International Joint Conference on Natural Language Processing (2017)


pdf (full)
bib (full)
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Greg Kondrak | Taro Watanabe

pdf bib
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
Yonatan Belinkov | Lluís Màrquez | Hassan Sajjad | Nadir Durrani | Fahim Dalvi | James Glass

While neural machine translation (NMT) models provide improved translation quality in an elegant framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially in higher quality models.

pdf bib
Context-Aware Smoothing for Neural Machine Translation
Kehai Chen | Rui Wang | Masao Utiyama | Eiichiro Sumita | Tiejun Zhao

In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information. This means that even if the word is in a different sentence context, it is represented as the fixed vector to learn source representation. Moreover, a large number of Out-Of-Vocabulary (OOV) words, which have different syntax and semantic information, are represented as the same vector representation of “unk”. To alleviate this problem, we propose a novel context-aware smoothing method to dynamically learn a sentence-specific vector for each word (including OOV words) depending on its local context words in a sentence. The learned context-aware representation is integrated into the NMT to improve the translation performance. Empirical results on NIST Chinese-to-English translation task show that the proposed approach achieves 1.78 BLEU improvements on average over a strong attentional NMT, and outperforms some existing systems.

Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information
An Nguyen Le | Ander Martinez | Akifumi Yoshimoto | Yuji Matsumoto

Sequence to Sequence Neural Machine Translation has achieved significant performance in recent years. Yet, there are some existing issues that Neural Machine Translation still does not solve completely. Two of them are translation for long sentences and the “over-translation”. To address these two problems, we propose an approach that utilize more grammatical information such as syntactic dependencies, so that the output can be generated based on more abundant information. In our approach, syntactic dependencies is employed in decoding. In addition, the output of the model is presented not as a simple sequence of tokens but as a linearized tree construction. In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure. Experiments on the Europarl-v7 dataset of French-to-English translation demonstrate that our proposed method improves BLEU scores by 1.57 and 2.40 on datasets consisting of sentences with up to 50 and 80 tokens, respectively. Furthermore, the proposed method also solved the two existing problems, ineffective translation for long sentences and over-translation in Neural Machine Translation.

What does Attention in Neural Machine Translation Pay Attention to?
Hamidreza Ghader | Christof Monz

Attention in neural machine translation provides the possibility to encode relevant parts of the source sentence at each translation step. As a result, attention is considered to be an alignment model as well. However, there is no work that specifically studies attention and provides analysis of what is being learned by attention models. Thus, the question still remains that how attention is similar or different from the traditional alignment. In this paper, we provide detailed analysis of attention and compare it to traditional alignment. We answer the question of whether attention is only capable of modelling translational equivalent or it captures more information. We show that attention is different from alignment in some cases and is capturing useful information other than alignments.

Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings
Masahiro Kaneko | Yuya Sakaizawa | Mamoru Komachi

In this study, we improve grammatical error detection by learning word embeddings that consider grammaticality and error patterns. Most existing algorithms for learning word embeddings usually model only the syntactic context of words so that classifiers treat erroneous and correct words as similar inputs. We address the problem of contextual information by considering learner errors. Specifically, we propose two models: one model that employs grammatical error patterns and another model that considers grammaticality of the target word. We determine grammaticality of n-gram sequence from the annotated error tags and extract grammatical error patterns for word embeddings from large-scale learner corpora. Experimental results show that a bidirectional long-short term memory model initialized by our word embeddings achieved the state-of-the-art accuracy by a large margin in an English grammatical error detection task on the First Certificate in English dataset.

Dependency Parsing with Partial Annotations: An Empirical Comparison
Yue Zhang | Zhenghua Li | Jun Lang | Qingrong Xia | Min Zhang

This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA). The first approach is based on a forest-based training objective for two CRF parsers, i.e., a biaffine neural network graph-based parser (Biaffine) and a traditional log-linear graph-based parser (LLGPar). The second approach is based on the idea of constrained decoding for three parsers, i.e., a traditional linear graph-based parser (LGPar), a globally normalized neural network transition-based parser (GN3Par) and a traditional linear transition-based parser (LTPar). For the test phase, constrained decoding is also used for completing partial trees. We conduct experiments on Penn Treebank under three different settings for simulating PA, i.e., random, most uncertain, and divergent outputs from the five parsers. The results show that LLGPar is most effective in directly learning from PA, and other parsers can achieve best performance when PAs are completed into full trees by LLGPar.

Neural Probabilistic Model for Non-projective MST Parsing
Xuezhe Ma | Eduard Hovy

In this paper, we propose a probabilistic parsing model that defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs. The neural network architecture is based on bi-directional LSTMCNNs, which automatically benefits from both word- and character-level representations, by using a combination of bidirectional LSTMs and CNNs. On top of the neural network, we introduce a probabilistic structured layer, defining a conditional log-linear model over non-projective trees. By exploiting Kirchhoff’s Matrix-Tree Theorem (Tutte, 1984), the partition functions and marginals can be computed efficiently, leading to a straightforward end-to-end model training procedure via back-propagation. We evaluate our model on 17 different datasets, across 14 different languages. Our parser achieves state-of-the-art parsing performance on nine datasets.

Word Ordering as Unsupervised Learning Towards Syntactically Plausible Word Representations
Noriki Nishida | Hideki Nakayama

The research question we explore in this study is how to obtain syntactically plausible word representations without using human annotations. Our underlying hypothesis is that word ordering tests, or linearizations, is suitable for learning syntactic knowledge about words. To verify this hypothesis, we develop a differentiable model called Word Ordering Network (WON) that explicitly learns to recover correct word order while implicitly acquiring word embeddings representing syntactic knowledge. We evaluate the word embeddings produced by the proposed method on downstream syntax-related tasks such as part-of-speech tagging and dependency parsing. The experimental results demonstrate that the WON consistently outperforms both order-insensitive and order-sensitive baselines on these tasks.

MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting
Tomoyuki Kajiwara | Mamoru Komachi | Daichi Mochihashi

We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition. Our paraphrase acquisition method first acquires lexical paraphrase pairs by bilingual pivoting and then reranks them by PMI and distributional similarity. The complementary nature of information from bilingual corpora and from monolingual corpora makes the proposed method robust. Experimental results show that the proposed method substantially outperforms bilingual pivoting and distributional similarity themselves in terms of metrics such as MRR, MAP, coverage, and Spearman’s correlation.

Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments
Quynh Ngoc Thi Do | Steven Bethard | Marie-Francine Moens

Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.

Natural Language Inference from Multiple Premises
Alice Lai | Yonatan Bisk | Julia Hockenmaier

We define a novel textual entailment task that requires inference over multiple premise sentences. We present a new dataset for this task that minimizes trivial lexical inferences, emphasizes knowledge of everyday events, and presents a more challenging setting for textual entailment. We evaluate several strong neural baselines and analyze how the multiple premise task differs from standard textual entailment.

Enabling Transitivity for Lexical Inference on Chinese Verbs Using Probabilistic Soft Logic
Wei-Chung Wang | Lun-Wei Ku

To learn more knowledge, enabling transitivity is a vital step for lexical inference. However, most of the lexical inference models with good performance are for nouns or noun phrases, which cannot be directly applied to the inference on events or states. In this paper, we construct the largest Chinese verb lexical inference dataset containing 18,029 verb pairs, where for each pair one of four inference relations are annotated. We further build a probabilistic soft logic (PSL) model to infer verb lexicons using the logic language. With PSL, we easily enable transitivity in two layers, the observed layer and the feature layer, which are included in the knowledge base. We further discuss the effect of transitives within and between these layers. Results show the performance of the proposed PSL model can be improved at least 3.5% (relative) when the transitivity is enabled. Furthermore, experiments show that enabling transitivity in the observed layer benefits the most.

An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
Marcin Junczys-Dowmunt | Roman Grundkiewicz

In this work, we explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputs mt (raw MT output) and src (source language input) in a single neural architecture, modeling {mt, src} → pe directly. Apart from that, we investigate the influence of hard-attention models which seem to be well-suited for monolingual tasks, as well as combinations of both ideas. We report results on data sets provided during the WMT-2016 shared task on automatic post-editing and can demonstrate that dual-attention models that incorporate all available data in the APE scenario in a single model improve on the best shared task system and on all other published results after the shared task. Dual-attention models that are combined with hard attention remain competitive despite applying fewer changes to the input.

Imagination Improves Multimodal Translation
Desmond Elliott | Ákos Kádár

We decompose multimodal translation into two sub-tasks: learning to translate and learning visually grounded representations. In a multitask learning framework, translations are learned in an attention-based encoder-decoder, and grounded representations are learned through image representation prediction. Our approach improves translation performance compared to the state of the art on the Multi30K dataset. Furthermore, it is equally effective if we train the image prediction task on the external MS COCO dataset, and we find improvements if we train the translation model on the external News Commentary parallel text.

Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder
Fahim Dalvi | Nadir Durrani | Hassan Sajjad | Yonatan Belinkov | Stephan Vogel

End-to-end training makes the neural machine translation (NMT) architecture simpler, yet elegant compared to traditional statistical machine translation (SMT). However, little is known about linguistic patterns of morphology, syntax and semantics learned during the training of NMT systems, and more importantly, which parts of the architecture are responsible for learning each of these phenomenon. In this paper we i) analyze how much morphology an NMT decoder learns, and ii) investigate whether injecting target morphology in the decoder helps it to produce better translations. To this end we present three methods: i) simultaneous translation, ii) joint-data learning, and iii) multi-task learning. Our results show that explicit morphological information helps the decoder learn target language morphology and improves the translation quality by 0.2–0.6 BLEU points.

Improving Neural Machine Translation through Phrase-based Forced Decoding
Jingyi Zhang | Masao Utiyama | Eiichro Sumita | Graham Neubig | Satoshi Nakamura

Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using the phrase-based decoding cost to rerank the n-best NMT outputs. The main challenge in implementing this approach is that NMT outputs may not be in the search space of the standard phrase-based decoding algorithm, because the search space of phrase-based SMT is limited by the phrase-based translation rule table. We propose a soft forced decoding algorithm, which can always successfully find a decoding path for any NMT output. We show that using the forced decoding cost to rerank the NMT outputs can successfully improve translation quality on four different language pairs.

Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation
Chunqi Wang | Bo Xu

Character-based sequence labeling framework is flexible and efficient for Chinese word segmentation (CWS). Recently, many character-based neural models have been applied to CWS. While they obtain good performance, they have two obvious weaknesses. The first is that they heavily rely on manually designed bigram feature, i.e. they are not good at capturing n-gram features automatically. The second is that they make no use of full word information. For the first weakness, we propose a convolutional neural model, which is able to capture rich n-gram features without any feature engineering. For the second one, we propose an effective approach to integrate the proposed model with word embeddings. We evaluate the model on two benchmark datasets: PKU and MSR. Without any feature engineering, the model obtains competitive performance — 95.7% on PKU and 97.3% on MSR. Armed with word embeddings, the model achieves state-of-the-art performance on both datasets — 96.5% on PKU and 98.0% on MSR, without using any external labeled resource.

Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
Yan Shao | Christian Hardmeier | Jörg Tiedemann | Joakim Nivre

We present a character-based model for joint segmentation and POS tagging for Chinese. The bidirectional RNN-CRF architecture for general sequence tagging is adapted and applied with novel vector representations of Chinese characters that capture rich contextual information and lower-than-character level features. The proposed model is extensively evaluated and compared with a state-of-the-art tagger respectively on CTB5, CTB9 and UD Chinese. The experimental results indicate that our model is accurate and robust across datasets in different sizes, genres and annotation schemes. We obtain state-of-the-art performance on CTB5, achieving 94.38 F1-score for joint segmentation and POS tagging.

Addressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure
Shen Huang | Xu Sun | Houfeng Wang

Boundary features are widely used in traditional Chinese Word Segmentation (CWS) methods as they can utilize unlabeled data to help improve the Out-of-Vocabulary (OOV) word recognition performance. Although various neural network methods for CWS have achieved performance competitive with state-of-the-art systems, these methods, constrained by the domain and size of the training corpus, do not work well in domain adaptation. In this paper, we propose a novel BLSTM-based neural network model which incorporates a global recurrent structure designed for modeling boundary features dynamically. Experiments show that the proposed structure can effectively boost the performance of Chinese Word Segmentation, especially OOV-Recall, which brings benefits to domain adaptation. We achieved state-of-the-art results on 6 domains of CNKI articles, and competitive results to the best reported on the 4 domains of SIGHAN Bakeoff 2010 data.

Information Bottleneck Inspired Method For Chat Text Segmentation
S Vishal | Mohit Yadav | Lovekesh Vig | Gautam Shroff

We present a novel technique for segmenting chat conversations using the information bottleneck method (Tishby et al., 2000), augmented with sequential continuity constraints. Furthermore, we utilize critical non-textual clues such as time between two consecutive posts and people mentions within the posts. To ascertain the effectiveness of the proposed method, we have collected data from public Slack conversations and Fresco, a proprietary platform deployed inside our organization. Experiments demonstrate that the proposed method yields an absolute (relative) improvement of as high as 3.23% (11.25%). To facilitate future research, we are releasing manual annotations for segmentation on public Slack conversations.

Distributional Modeling on a Diet: One-shot Word Learning from Text Only
Su Wang | Stephen Roller | Katrin Erk

We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative.

A Computational Study on Word Meanings and Their Distributed Representations via Polymodal Embedding
Joohee Park | Sung-hyon Myaeng

A distributed representation has become a popular approach to capturing a word meaning. Besides its success and practical value, however, questions arise about the relationships between a true word meaning and its distributed representation. In this paper, we examine such a relationship via polymodal embedding approach inspired by the theory that humans tend to use diverse sources in developing a word meaning. The result suggests that the existing embeddings lack in capturing certain aspects of word meanings which can be significantly improved by the polymodal approach. Also, we show distinct characteristics of different types of words (e.g. concreteness) via computational studies. Finally, we show our proposed embedding method outperforms the baselines in the word similarity measure tasks and the hypernym prediction tasks.

Geographical Evaluation of Word Embeddings
Michal Konkol | Tomáš Brychcín | Michal Nykl | Tomáš Hercig

Word embeddings are commonly compared either with human-annotated word similarities or through improvements in natural language processing tasks. We propose a novel principle which compares the information from word embeddings with reality. We implement this principle by comparing the information in the word embeddings with geographical positions of cities. Our evaluation linearly transforms the semantic space to optimally fit the real positions of cities and measures the deviation between the position given by word embeddings and the real position. A set of well-known word embeddings with state-of-the-art results were evaluated. We also introduce a visualization that helps with error analysis.

On Modeling Sense Relatedness in Multi-prototype Word Embedding
Yixin Cao | Jiaxin Shi | Juanzi Li | Zhiyuan Liu | Chengjiang Li

To enhance the expression ability of distributional word representation learning model, many researchers tend to induce word senses through clustering, and learn multiple embedding vectors for each word, namely multi-prototype word embedding model. However, most related work ignores the relatedness among word senses which actually plays an important role. In this paper, we propose a novel approach to capture word sense relatedness in multi-prototype word embedding model. Particularly, we differentiate the original sense and extended senses of a word by introducing their global occurrence information and model their relatedness through the local textual context information. Based on the idea of fuzzy clustering, we introduce a random process to integrate these two types of senses and design two non-parametric methods for word sense induction. To make our model more scalable and efficient, we use an online joint learning framework extended from the Skip-gram model. The experimental results demonstrate that our model outperforms both conventional single-prototype embedding models and other multi-prototype embedding models, and achieves more stable performance when trained on smaller data.

Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context
Ryu Takeda | Kazunori Komatani

Unsupervised segmentation of phoneme sequences is an essential process to obtain unknown words during spoken dialogues. In this segmentation, an input phoneme sequence without delimiters is converted into segmented sub-sequences corresponding to words. The Pitman-Yor semi-Markov model (PYSMM) is promising for this problem, but its performance degrades when it is applied to phoneme-level word segmentation. This is because of insufficient cues for the segmentation, e.g., homophones are improperly treated as single entries and their different contexts are also confused. We propose a phoneme-length context model for PYSMM to give a helpful cue at the phoneme-level and to predict succeeding segments more accurately. Our experiments showed that the peak performance with our context model outperformed those without such a context model by 0.045 at most in terms of F-measures of estimated segmentation.

A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification
Ye Zhang | Byron Wallace

Convolutional Neural Networks (CNNs) have recently achieved remarkably strong performance on the practically important task of sentence classification (Kim, 2014; Kalchbrenner et al., 2014; Johnson and Zhang, 2014; Zhang et al., 2016). However, these models require practitioners to specify an exact model architecture and set accompanying hyperparameters, including the filter region size, regularization parameters, and so on. It is currently unknown how sensitive model performance is to changes in these configurations for the task of sentence classification. We thus conduct a sensitivity analysis of one-layer CNNs to explore the effect of architecture components on model performance; our aim is to distinguish between important and comparatively inconsequential design decisions for sentence classification. We focus on one-layer CNNs (to the exclusion of more complex models) due to their comparative simplicity and strong empirical performance, which makes it a modern standard baseline method akin to Support Vector Machine (SVMs) and logistic regression. We derive practical advice from our extensive empirical results for those interested in getting the most out of CNNs for sentence classification in real world settings.

Coordination Boundary Identification with Similarity and Replaceability
Hiroki Teranishi | Hiroyuki Shindo | Yuji Matsumoto

We propose a neural network model for coordination boundary detection. Our method relies on the two common properties - similarity and replaceability in conjuncts - in order to detect both similar pairs of conjuncts and dissimilar pairs of conjuncts. The model improves identification of clause-level coordination using bidirectional RNNs incorporating two properties as features. We show that our model outperforms the existing state-of-the-art methods on the coordination annotated Penn Treebank and Genia corpus without any syntactic information from parsers.

Turning Distributional Thesauri into Word Vectors for Synonym Extraction and Expansion
Olivier Ferret

In this article, we propose to investigate a new problem consisting in turning a distributional thesaurus into dense word vectors. We propose more precisely a method for performing such task by associating graph embedding and distributed representation adaptation. We have applied and evaluated it for English nouns at a large scale about its ability to retrieve synonyms. In this context, we have also illustrated the interest of the developed method for three different tasks: the improvement of already existing word embeddings, the fusion of heterogeneous representations and the expansion of synsets.

Training Word Sense Embeddings With Lexicon-based Regularization
Luis Nieto-Piña | Richard Johansson

We propose to improve word sense embeddings by enriching an automatic corpus-based method with lexicographic data. Information from a lexicon is introduced into the learning algorithm’s objective function through a regularizer. The incorporation of lexicographic data yields embeddings that are able to reflect expert-defined word senses, while retaining the robustness, high quality, and coverage of automatic corpus-based methods. These properties are observed in a manual inspection of the semantic clusters that different degrees of regularizer strength create in the vector space. Moreover, we evaluate the sense embeddings in two downstream applications: word sense disambiguation and semantic frame prediction, where they outperform simpler approaches. Our results show that a corpus-based model balanced with lexicographic data learns better representations and improve their performance in downstream tasks.

Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs
Fernando Alva-Manchego | Joachim Bingel | Gustavo Paetzold | Carolina Scarton | Lucia Specia

Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. End-to-end models also make it hard to interpret what is actually learned from data. We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model.

Domain-Adaptable Hybrid Generation of RDF Entity Descriptions
Or Biran | Kathleen McKeown

RDF ontologies provide structured data on entities in many domains and continue to grow in size and diversity. While they can be useful as a starting point for generating descriptions of entities, they often miss important information about an entity that cannot be captured as simple relations. In addition, generic approaches to generation from RDF cannot capture the unique style and content of specific domains. We describe a framework for hybrid generation of entity descriptions, which combines generation from RDF data with text extracted from a corpus, and extracts unique aspects of the domain from the corpus to create domain-specific generation systems. We show that each component of our approach significantly increases the satisfaction of readers with the text across multiple applications and domains.

ES-LDA: Entity Summarization using Knowledge-based Topic Modeling
Seyedamin Pouriyeh | Mehdi Allahyari | Krzysztof Kochut | Gong Cheng | Hamid Reza Arabnia

With the advent of the Internet, the amount of Semantic Web documents that describe real-world entities and their inter-links as a set of statements have grown considerably. These descriptions are usually lengthy, which makes the utilization of the underlying entities a difficult task. Entity summarization, which aims to create summaries for real-world entities, has gained increasing attention in recent years. In this paper, we propose a probabilistic topic model, ES-LDA, that combines prior knowledge with statistical learning techniques within a single framework to create more reliable and representative summaries for entities. We demonstrate the effectiveness of our approach by conducting extensive experiments and show that our model outperforms the state-of-the-art techniques and enhances the quality of the entity summaries.

Procedural Text Generation from an Execution Video
Atsushi Ushiku | Hayato Hashimoto | Atsushi Hashimoto | Shinsuke Mori

In recent years, there has been a surge of interest in automatically describing images or videos in a natural language. These descriptions are useful for image/video search, etc. In this paper, we focus on procedure execution videos, in which a human makes or repairs something and propose a method for generating procedural texts from them. Since video/text pairs available are limited in size, the direct application of end-to-end deep learning is not feasible. Thus we propose to train Faster R-CNN network for object recognition and LSTM for text generation and combine them at run time. We took pairs of recipe and cooking video, generated a recipe from a video, and compared it with the original recipe. The experimental results showed that our method can produce a recipe as accurate as the state-of-the-art scene descriptions.

Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information
Ling Gan | Houyu Gong

Tree-structured Long Short-Term Memory (Tree-LSTM) has been proved to be an effective method in the sentiment analysis task. It extracts structural information on text, and uses Long Short-Term Memory (LSTM) cell to prevent gradient vanish. However, though combining the LSTM cell, it is still a kind of model that extracts the structural information and almost not extracts serialization information. In this paper, we propose three new models in order to combine those two kinds of information: the structural information generated by the Constituency Tree-LSTM and the serialization information generated by Long-Short Term Memory neural network. Our experiments show that combining those two kinds of information can give contributes to the performance of the sentiment analysis task compared with the single Constituency Tree-LSTM model and the LSTM model.

Length, Interchangeability, and External Knowledge: Observations from Predicting Argument Convincingness
Peter Potash | Robin Bhattacharya | Anna Rumshisky

In this work, we provide insight into three key aspects related to predicting argument convincingness. First, we explicitly display the power that text length possesses for predicting convincingness in an unsupervised setting. Second, we show that a bag-of-words embedding model posts state-of-the-art on a dataset of arguments annotated for convincingness, outperforming an SVM with numerous hand-crafted features as well as recurrent neural network models that attempt to capture semantic composition. Finally, we assess the feasibility of integrating external knowledge when predicting convincingness, as arguments are often more convincing when they contain abundant information and facts. We finish by analyzing the correlations between the various models we propose.

Exploiting Document Level Information to Improve Event Detection via Recurrent Neural Networks
Shaoyang Duan | Ruifang He | Wenli Zhao

This paper tackles the task of event detection, which involves identifying and categorizing events. The previous work mainly exist two problems: (1) the traditional feature-based methods apply cross-sentence information, yet need taking a large amount of human effort to design complicated feature sets and inference rules; (2) the representation-based methods though overcome the problem of manually extracting features, while just depend on local sentence representation. Considering local sentence context is insufficient to resolve ambiguities in identifying particular event types, therefore, we propose a novel document level Recurrent Neural Networks (DLRNN) model, which can automatically extract cross-sentence clues to improve sentence level event detection without designing complex reasoning rules. Experiment results show that our approach outperforms other state-of-the-art methods on ACE 2005 dataset without external knowledge base.

Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging
Boliang Zhang | Di Lu | Xiaoman Pan | Ying Lin | Halidanmu Abudukelimu | Heng Ji | Kevin Knight

Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge. All supervised learning methods (including deep neural networks (DNN)) are sensitive to noise and thus they are not quite portable without massive clean annotations. We found that the F-scores of DNN-based name taggers drop rapidly (20%-30%) when we replace clean manual annotations with noisy annotations in the training data. We propose a new solution to incorporate many non-traditional language universal resources that are readily available but rarely explored in the Natural Language Processing (NLP) community, such as the World Atlas of Linguistic Structure, CIA names, PanLex and survival guides. We acquire and encode various types of non-traditional linguistic resources into a DNN name tagger. Experiments on three low-resource languages show that feeding linguistic knowledge can make DNN significantly more robust to noise, achieving 8%-22% absolute F-score gains on name tagging without using any human annotation

NMT or SMT: Case Study of a Narrow-domain English-Latvian Post-editing Project
Inguna Skadiņa | Mārcis Pinnis

The recent technological shift in machine translation from statistical machine translation (SMT) to neural machine translation (NMT) raises the question of the strengths and weaknesses of NMT. In this paper, we present an analysis of NMT and SMT systems’ outputs from narrow domain English-Latvian MT systems that were trained on a rather small amount of data. We analyze post-edits produced by professional translators and manually annotated errors in these outputs. Analysis of post-edits allowed us to conclude that both approaches are comparably successful, allowing for an increase in translators’ productivity, with the NMT system showing slightly worse results. Through the analysis of annotated errors, we found that NMT translations are more fluent than SMT translations. However, errors related to accuracy, especially, mistranslation and omission errors, occur more often in NMT outputs. The word form errors, that characterize the morphological richness of Latvian, are frequent for both systems, but slightly fewer in NMT outputs.

Towards Neural Machine Translation with Partially Aligned Corpora
Yining Wang | Yang Zhao | Jiajun Zhang | Chengqing Zong | Zhengshan Xue

While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in which there only exists monolingual corpora and phrase pairs. We propose a new method towards translation with partially aligned sentence pairs which are derived from the phrase pairs and monolingual corpora. To make full use of the partially aligned corpora, we adapt the conventional NMT training method in two aspects. On one hand, different generation strategies are designed for aligned and unaligned target words. On the other hand, a different objective function is designed to model the partially aligned parts. The experiments demonstrate that our method can achieve a relatively good result in such a translation scenario, and tiny bitexts can boost translation quality to a large extent.

Identifying Usage Expression Sentences in Consumer Product Reviews
Shibamouli Lahiri | V.G.Vinod Vydiswaran | Rada Mihalcea

In this paper we introduce the problem of identifying usage expression sentences in a consumer product review. We create a human-annotated gold standard dataset of 565 reviews spanning five distinct product categories. Our dataset consists of more than 3,000 annotated sentences. We further introduce a classification system to label sentences according to whether or not they describe some “usage”. The system combines lexical, syntactic, and semantic features in a product-agnostic fashion to yield good classification performance. We show the effectiveness of our approach using importance ranking of features, error analysis, and cross-product classification experiments.

Between Reading Time and Syntactic/Semantic Categories
Masayuki Asahara | Sachi Kato

This article presents a contrastive analysis between reading time and syntactic/semantic categories in Japanese. We overlaid the reading time annotation of BCCWJ-EyeTrack and a syntactic/semantic category information annotation on the ‘Balanced Corpus of Contemporary Written Japanese’. Statistical analysis based on a mixed linear model showed that verbal phrases tend to have shorter reading times than adjectives, adverbial phrases, or nominal phrases. The results suggest that the preceding phrases associated with the presenting phrases promote the reading process to shorten the gazing time.

WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition
Abbas Ghaddar | Phillippe Langlais

We revisit the idea of mining Wikipedia in order to generate named-entity annotations. We propose a new methodology that we applied to English Wikipedia to build WiNER, a large, high quality, annotated corpus. We evaluate its usefulness on 6 NER tasks, comparing 4 popular state-of-the art approaches. We show that LSTM-CRF is the approach that benefits the most from our corpus. We report impressive gains with this model when using a small portion of WiNER on top of the CONLL training material. Last, we propose a simple but efficient method for exploiting the full range of WiNER, leading to further improvements.

Reusing Neural Speech Representations for Auditory Emotion Recognition
Egor Lakomkin | Cornelius Weber | Sven Magg | Stefan Wermter

Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion perception resulting in low annotator agreement, and the uncertainty about which features are the most relevant and robust ones for classification. In this paper, we will tackle the latter problem. Inspired by the recent success of transfer learning methods we propose a set of architectures which utilize neural representations inferred by training on large speech databases for the acoustic emotion recognition task. Our experiments on the IEMOCAP dataset show ~10% relative improvements in the accuracy and F1-score over the baseline recurrent neural network which is trained end-to-end for emotion recognition.

Local Monotonic Attention Mechanism for End-to-End Speech And Language Processing
Andros Tjandra | Sakriani Sakti | Satoshi Nakamura

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target sequence. Most attentional mechanisms used today is based on a global attention property which requires a computation of a weighted summarization of the whole input sequence generated by encoder states. However, it is computationally expensive and often produces misalignment on the longer input sequence. Furthermore, it does not fit with monotonous or left-to-right nature in several tasks, such as automatic speech recognition (ASR), grapheme-to-phoneme (G2P), etc. In this paper, we propose a novel attention mechanism that has local and monotonic properties. Various ways to control those properties are also explored. Experimental results on ASR, G2P and machine translation between two languages with similar sentence structures, demonstrate that the proposed encoder-decoder model with local monotonic attention could achieve significant performance improvements and reduce the computational complexity in comparison with the one that used the standard global attention architecture.

Attentive Language Models
Giancarlo Salton | Robert Ross | John Kelleher

In this paper, we extend Recurrent Neural Network Language Models (RNN-LMs) with an attention mechanism. We show that an “attentive” RNN-LM (with 11M parameters) achieves a better perplexity than larger RNN-LMs (with 66M parameters) and achieves performance comparable to an ensemble of 10 similar sized RNN-LMs. We also show that an “attentive” RNN-LM needs less contextual information to achieve similar results to the state-of-the-art on the wikitext2 dataset.

Diachrony-aware Induction of Binary Latent Representations from Typological Features
Yugo Murawaki

Although features of linguistic typology are a promising alternative to lexical evidence for tracing evolutionary history of languages, a large number of missing values in the dataset pose serious difficulties for statistical modeling. In this paper, we combine two existing approaches to the problem: (1) the synchronic approach that focuses on interdependencies between features and (2) the diachronic approach that exploits phylogenetically- and/or spatially-related languages. Specifically, we propose a Bayesian model that (1) represents each language as a sequence of binary latent parameters encoding inter-feature dependencies and (2) relates a language’s parameters to those of its phylogenetic and spatial neighbors. Experiments show that the proposed model recovers missing values more accurately than others and that induced representations retain phylogenetic and spatial signals observed for surface features.

Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
Nasrin Mostafazadeh | Chris Brockett | Bill Dolan | Michel Galley | Jianfeng Gao | Georgios Spithourakis | Lucy Vanderwende

The popularity of image sharing on social media and the engagement it creates between users reflect the important role that visual context plays in everyday conversations. We present a novel task, Image Grounded Conversations (IGC), in which natural-sounding conversations are generated about a shared image. To benchmark progress, we introduce a new multiple reference dataset of crowd-sourced, event-centric conversations on images. IGC falls on the continuum between chit-chat and goal-directed conversation models, where visual grounding constrains the topic of conversation to event-driven utterances. Experiments with models trained on social media data show that the combination of visual and textual context enhances the quality of generated conversational turns. In human evaluation, the gap between human performance and that of both neural and retrieval architectures suggests that multi-modal IGC presents an interesting challenge for dialog research.

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
Sosuke Kobayashi | Naoaki Okazaki | Kentaro Inui

This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models. We proposed a method for on-the-fly construction and exploitation of word embeddings in both the input and output layers of a neural model by tracking contexts. This extends the dynamic entity representation used in Kobayashi et al. (2016) and incorporates a copy mechanism proposed independently by Gu et al. (2016) and Gulcehre et al. (2016). In addition, we construct a new task and dataset called Anonymized Language Modeling for evaluating the ability to capture word meanings while reading. Experiments conducted using our novel dataset show that the proposed variant of RNN language model outperformed the baseline model. Furthermore, the experiments also demonstrate that dynamic updates of an output layer help a model predict reappearing entities, whereas those of an input layer are effective to predict words following reappearing entities.

Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification
Wei Shi | Frances Yung | Raphael Rubino | Vera Demberg

Implicit discourse relation recognition is an extremely challenging task due to the lack of indicative connectives. Various neural network architectures have been proposed for this task recently, but most of them suffer from the shortage of labeled data. In this paper, we address this problem by procuring additional training data from parallel corpora: When humans translate a text, they sometimes add connectives (a process known as explicitation). We automatically back-translate it into an English connective and use it to infer a label with high confidence. We show that a training set several times larger than the original training set can be generated this way. With the extra labeled instances, we show that even a simple bidirectional Long Short-Term Memory Network can outperform the current state-of-the-art.

Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
Yizhong Wang | Sujian Li | Jingfeng Yang | Xu Sun | Houfeng Wang

Identifying implicit discourse relations between text spans is a challenging task because it requires understanding the meaning of the text. To tackle this task, recent studies have tried several deep learning methods but few of them exploited the syntactic information. In this work, we explore the idea of incorporating syntactic parse tree into neural networks. Specifically, we employ the Tree-LSTM model and Tree-GRU model, which is based on the tree structure, to encode the arguments in a relation. And we further leverage the constituent tags to control the semantic composition process in these tree-structured neural networks. Experimental results show that our method achieves state-of-the-art performance on PDTB corpus.

Cross-Lingual Sentiment Analysis Without (Good) Translation
Mohamed Abdalla | Graeme Hirst

Current approaches to cross-lingual sentiment analysis try to leverage the wealth of labeled English data using bilingual lexicons, bilingual vector space embeddings, or machine translation systems. Here we show that it is possible to use a single linear transformation, with as few as 2000 word pairs, to capture fine-grained sentiment relationships between words in a cross-lingual setting. We apply these cross-lingual sentiment models to a diverse set of tasks to demonstrate their functionality in a non-English context. By effectively leveraging English sentiment knowledge without the need for accurate translation, we can analyze and extract features from other languages with scarce data at a very low cost, thus making sentiment and related analyses for many languages inexpensive.

Implicit Syntactic Features for Target-dependent Sentiment Analysis
Yuze Gao | Yue Zhang | Tong Xiao

Targeted sentiment analysis investigates the sentiment polarities on given target mentions from input texts. Different from sentence level sentiment, it offers more fine-grained knowledge on each entity mention. While early work leveraged syntactic information, recent research has used neural representation learning to induce features automatically, thereby avoiding error propagation of syntactic parsers, which are particularly severe on social media texts. We study a method to leverage syntactic information without explicitly building the parser outputs, by training an encoder-decoder structure parser model on standard syntactic treebanks, and then leveraging its hidden encoder layers when analysing tweets. Such hidden vectors do not contain explicit syntactic outputs, yet encode rich syntactic features. We use them to augment the inputs to a baseline state-of-the-art targeted sentiment classifier, observing significant improvements on various benchmark datasets. We obtain the best accuracies on all test sets.

Graph Based Sentiment Aggregation using ConceptNet Ontology
Srikanth Tamilselvam | Seema Nagar | Abhijit Mishra | Kuntal Dey

The sentiment aggregation problem accounts for analyzing the sentiment of a user towards various aspects/features of a product, and meaningfully assimilating the pragmatic significance of these features/aspects from an opinionated text. The current paper addresses the sentiment aggregation problem, by assigning weights to each aspect appearing in the user-generated content, that are proportionate to the strategic importance of the aspect in the pragmatic domain. The novelty of this paper is in computing the pragmatic significance (weight) of each aspect, using graph centrality measures (applied on domain specific ontology-graphs extracted from ConceptNet), and deeply ingraining these weights while aggregating the sentiments from opinionated text. We experiment over multiple real-life product review data. Our system consistently outperforms the state of the art - by as much as a F-score of 20.39% in one case.

Sentence Modeling with Deep Neural Architecture using Lexicon and Character Attention Mechanism for Sentiment Classification
Huy Thanh Nguyen | Minh Le Nguyen

Tweet-level sentiment classification in Twitter social networking has many challenges: exploiting syntax, semantic, sentiment, and context in tweets. To address these problems, we propose a novel approach to sentiment analysis that uses lexicon features for building lexicon embeddings (LexW2Vs) and generates character attention vectors (CharAVs) by using a Deep Convolutional Neural Network (DeepCNN). Our approach integrates LexW2Vs and CharAVs with continuous word embeddings (ContinuousW2Vs) and dependency-based word embeddings (DependencyW2Vs) simultaneously in order to increase information for each word into a Bidirectional Contextual Gated Recurrent Neural Network (Bi-CGRNN). We evaluate our model on two Twitter sentiment classification datasets. Experimental results show that our model can improve the classification accuracy of sentence-level sentiment analysis in Twitter social networking.

Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising
Yiping Jin | Dittaya Wanvarie | Phu Le

In this paper we propose a lightly-supervised framework to rapidly build text classifiers for contextual advertising. Traditionally text classification techniques require labeled training documents for each predefined class. In the scenario of contextual advertising, advertisers often want to target to a specific class of webpages most relevant to their product or service, which may not be covered by a pre-trained classifier. Moreover, the advertisers are interested in whether a webpage is “relevant” or “irrelevant”. It is time-consuming to solicit the advertisers for reliable training signals for the negative class. Therefore, it is more suitable to model the problem as a one-class classification problem, in contrast to traditional classification problems where disjoint classes are defined a priori. We first apply two state-of-the-art lightly-supervised classification models, generalized expectation (GE) criteria (Druck et al., 2008) and multinomial naive Bayes (MNB) with priors (Settles, 2011) to one-class classification where the user only needs to provide a small list of labeled words for the target class. To combine the strengths of the two models, we fuse them together by using MNB to automatically enrich the constraints for GE training. We also explore ensemble method to combine classifiers. On a corpus of webpages from real-time bidding requests, the proposed model achieves the highest average F1 of 0.69 and closes more than half of the gap between previous state-of-the-art lightly-supervised models to a fully-supervised MaxEnt model.

Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields
Fei Liu | Timothy Baldwin | Trevor Cohn

Despite successful applications across a broad range of NLP tasks, conditional random fields (“CRFs”), in particular the linear-chain variant, are only able to model local features. While this has important benefits in terms of inference tractability, it limits the ability of the model to capture long-range dependencies between items. Attempts to extend CRFs to capture long-range dependencies have largely come at the cost of computational complexity and approximate inference. In this work, we propose an extension to CRFs by integrating external memory, taking inspiration from memory networks, thereby allowing CRFs to incorporate information far beyond neighbouring steps. Experiments across two tasks show substantial improvements over strong CRF and LSTM baselines.

Named Entity Recognition with Stack Residual LSTM and Trainable Bias Decoding
Quan Tran | Andrew MacKinlay | Antonio Jimeno Yepes

Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition (NER). We present two innovations to improve the performance of these models. The first innovation is the introduction of residual connections between the Stacked Recurrent Neural Network model to address the degradation problem of deep neural networks. The second innovation is a bias decoding mechanism that allows the trained system to adapt to non-differentiable and externally computed objectives, such as the entity-based F-measure. Our work improves the state-of-the-art results for both Spanish and English languages on the standard train/development/test split of the CoNLL 2003 Shared Task NER dataset.

Neuramanteau: A Neural Network Ensemble Model for Lexical Blends
Kollol Das | Shaona Ghosh

The problem of blend formation in generative linguistics is interesting in the context of neologism, their quick adoption in modern life and the creative generative process guiding their formation. Blend quality depends on multitude of factors with high degrees of uncertainty. In this work, we investigate if the modern neural network models can sufficiently capture and recognize the creative blend composition process. We propose recurrent neural network sequence-to-sequence models, that are evaluated on multiple blend datasets available in the literature. We propose an ensemble neural and hybrid model that outperforms most of the baselines and heuristic models upon evaluation on test data.

Leveraging Discourse Information Effectively for Authorship Attribution
Elisa Ferracane | Su Wang | Raymond Mooney

We explore techniques to maximize the effectiveness of discourse information in the task of authorship attribution. We present a novel method to embed discourse features in a Convolutional Neural Network text classifier, which achieves a state-of-the-art result by a significant margin. We empirically investigate several featurization methods to understand the conditions under which discourse features contribute non-trivial performance gains, and analyze discourse embeddings.

Lightly-Supervised Modeling of Argument Persuasiveness
Isaac Persing | Vincent Ng

We propose the first lightly-supervised approach to scoring an argument’s persuasiveness. Key to our approach is the novel hypothesis that lightly-supervised persuasiveness scoring is possible by explicitly modeling the major errors that negatively impact persuasiveness. In an evaluation on a new annotated corpus of online debate arguments, our approach rivals its fully-supervised counterparts in performance by four scoring metrics when using only 10% of the available training instances.

Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
Yi Luan | Chris Brockett | Bill Dolan | Jianfeng Gao | Michel Galley

Building a persona-based conversation agent is challenging owing to the lack of large amounts of speaker-specific conversation data for model training. This paper addresses the problem by proposing a multi-task learning approach to training neural conversation models that leverages both conversation data across speakers and other types of data pertaining to the speaker and speaker roles to be modeled. Experiments show that our approach leads to significant improvements over baseline model quality, generating responses that capture more precisely speakers’ traits and speaking styles. The model offers the benefits of being algorithmically simple and easy to implement, and not relying on large quantities of data representing specific individual speakers.

Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks
Shikib Mehri | Giuseppe Carenini

Thread disentanglement is a precursor to any high-level analysis of multiparticipant chats. Existing research approaches the problem by calculating the likelihood of two messages belonging in the same thread. Our approach leverages a newly annotated dataset to identify reply relationships. Furthermore, we explore the usage of an RNN, along with large quantities of unlabeled data, to learn semantic relationships between messages. Our proposed pipeline, which utilizes a reply classifier and an RNN to generate a set of disentangled threads, is novel and performs well against previous work.

Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features
Marc Schulder | Michael Wiegand | Josef Ruppenhofer | Benjamin Roth

We present a major step towards the creation of the first high-coverage lexicon of polarity shifters. In this work, we bootstrap a lexicon of verbs by exploiting various linguistic features. Polarity shifters, such as “abandon”, are similar to negations (e.g. “not”) in that they move the polarity of a phrase towards its inverse, as in “abandon all hope”. While there exist lists of negation words, creating comprehensive lists of polarity shifters is far more challenging due to their sheer number. On a sample of manually annotated verbs we examine a variety of linguistic features for this task. Then we build a supervised classifier to increase coverage. We show that this approach drastically reduces the annotation effort while ensuring a high-precision lexicon. We also show that our acquired knowledge of verbal polarity shifters improves phrase-level sentiment analysis.

Cascading Multiway Attentions for Document-level Sentiment Classification
Dehong Ma | Sujian Li | Xiaodong Zhang | Houfeng Wang | Xu Sun

Document-level sentiment classification aims to assign the user reviews a sentiment polarity. Previous methods either just utilized the document content without consideration of user and product information, or did not comprehensively consider what roles the three kinds of information play in text modeling. In this paper, to reasonably use all the information, we present the idea that user, product and their combination can all influence the generation of attentions to words and sentences, when judging the sentiment of a document. With this idea, we propose a cascading multiway attention (CMA) model, where multiple ways of using user and product information are cascaded to influence the generation of attentions on the word and sentence layers. Then, sentences and documents are well modeled by multiple representation vectors, which provide rich information for sentiment classification. Experiments on IMDB and Yelp datasets demonstrate the effectiveness of our model.

An Ensemble Method with Sentiment Features and Clustering Support
Huy Tien Nguyen | Minh Le Nguyen

Deep learning models have recently been applied successfully in natural language processing, especially sentiment analysis. Each deep learning model has a particular advantage, but it is difficult to combine these advantages into one model, especially in the area of sentiment analysis. In our approach, Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) were utilized to learn sentiment-specific features in a freezing scheme. This scenario provides a novel and efficient way for integrating advantages of deep learning models. In addition, we also grouped documents into clusters by their similarity and applied the prediction score of Naive Bayes SVM (NBSVM) method to boost the classification accuracy of each group. The experiments show that our method achieves the state-of-the-art performance on two well-known datasets: IMDB large movie reviews for document level and Pang & Lee movie reviews for sentence level.

Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification
Jianfei Yu | Jing Jiang

In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification. We first design a new auxiliary task based on sentiment scores of domain-independent words. We then propose two neural network architectures to respectively induce document embeddings and sentence embeddings that work well for different domains. When these document and sentence embeddings are used for sentiment classification, we find that with both pseudo and external sentiment lexicons, our proposed methods can perform similarly to or better than several highly competitive domain adaptation methods on a benchmark dataset of product reviews.

Measuring Semantic Relations between Human Activities
Steven Wilson | Rada Mihalcea

The things people do in their daily lives can provide valuable insights into their personality, values, and interests. Unstructured text data on social media platforms are rich in behavioral content, and automated systems can be deployed to learn about human activity on a broad scale if these systems are able to reason about the content of interest. In order to aid in the evaluation of such systems, we introduce a new phrase-level semantic textual similarity dataset comprised of human activity phrases, providing a testbed for automated systems that analyze relationships between phrasal descriptions of people’s actions. Our set of 1,000 pairs of activities is annotated by human judges across four relational dimensions including similarity, relatedness, motivational alignment, and perceived actor congruence. We evaluate a set of strong baselines for the task of generating scores that correlate highly with human ratings, and we introduce several new approaches to the phrase-level similarity task in the domain of human activities.

Learning Transferable Representation for Bilingual Relation Extraction via Convolutional Neural Networks
Bonan Min | Zhuolin Jiang | Marjorie Freedman | Ralph Weischedel

Typically, relation extraction models are trained to extract instances of a relation ontology using only training data from a single language. However, the concepts represented by the relation ontology (e.g. ResidesIn, EmployeeOf) are language independent. The numbers of annotated examples available for a given ontology vary between languages. For example, there are far fewer annotated examples in Spanish and Japanese than English and Chinese. Furthermore, using only language-specific training data results in the need to manually annotate equivalently large amounts of training for each new language a system encounters. We propose a deep neural network to learn transferable, discriminative bilingual representation. Experiments on the ACE 2005 multilingual training corpus demonstrate that the joint training process results in significant improvement in relation classification performance over the monolingual counterparts. The learnt representation is discriminative and transferable between languages. When using 10% (25K English words, or 30K Chinese characters) of the training data, our approach results in doubling F1 compared to a monolingual baseline. We achieve comparable performance to the monolingual system trained with 250K English words (or 300K Chinese characters) With 50% of training data.

Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora
Amir Hazem | Emmanuel Morin

Bilingual lexicon extraction from comparable corpora is constrained by the small amount of available data when dealing with specialized domains. This aspect penalizes the performance of distributional-based approaches, which is closely related to the reliability of word’s cooccurrence counts extracted from comparable corpora. A solution to avoid this limitation is to associate external resources with the comparable corpus. Since bilingual word embeddings have recently shown efficient models for learning bilingual distributed representation of words, we explore different word embedding models and show how a general-domain comparable corpus can enrich a specialized comparable corpus via neural networks

A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering
Luigi Yu-Cheng Liu | Damien Nouvel

In many languages such as Bambara or Arabic, tone markers (diacritics) may be written but are actually often omitted. NLP applications are confronted to ambiguities and subsequent difficulties when processing texts. To circumvent this problem, tonalization may be used, as a word sense disambiguation task, relying on context to add diacritics that partially disambiguate words as well as senses. In this paper, we describe our implementation of a Bambara tonalizer that adds tone markers using machine learning (CRFs). To make our tool efficient, we used differential coding, word segmentation and edit operation filtering. We describe our approach that allows tractable machine learning and improves accuracy: our model may be learned within minutes on a 358K-word corpus and reaches 92.3% accuracy.

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
Tianyu Zhao | Tatsuya Kawahara

Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model’s performance on both of the tasks. Compared with past joint models, the proposed architecture can (1) incorporate contextual information in dialog act recognition, and (2) integrate models for tasks of different levels as a whole, i.e. dialog act segmentation on the word level and dialog act recognition on the segment level. Experimental results show that the joint training system outperforms the simple cascading system and the joint coding system on both dialog act segmentation and recognition tasks.

Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues
Xin Wang | Jianan Wang | Yuanchao Liu | Xiaolong Wang | Zhuoran Wang | Baoxun Wang

User experience is essential for human-computer dialogue systems. However, it is impractical to ask users to provide explicit feedbacks when the agents’ responses displease them. Therefore, in this paper, we explore to predict users’ imminent dissatisfactions caused by intelligent agents by analysing the existing utterances in the dialogue sessions. To our knowledge, this is the first work focusing on this task. Several possible factors that trigger negative emotions are modelled. A relation sequence model (RSM) is proposed to encode the sequence of appropriateness of current response with respect to the earlier utterances. The experimental results show that the proposed structure is effective in modelling emotional risk (possibility of negative feedback) than existing conversation modelling approaches. Besides, strategies of obtaining distance supervision data for pre-training are also discussed in this work. Balanced sampling with respect to the last response in the distance supervision data are shown to be reliable for data augmentation.

Finding Dominant User Utterances And System Responses in Conversations
Dhiraj Madan | Sachindra Joshi

There are several dialog frameworks which allow manual specification of intents and rule based dialog flow. The rule based framework provides good control to dialog designers at the expense of being more time consuming and laborious. The job of a dialog designer can be reduced if we could identify pairs of user intents and corresponding responses automatically from prior conversations between users and agents. In this paper we propose an approach to find these frequent user utterances (which serve as examples for intents) and corresponding agent responses. We propose a novel SimCluster algorithm that extends standard K-means algorithm to simultaneously cluster user utterances and agent utterances by taking their adjacency information into account. The method also aligns these clusters to provide pairs of intents and response groups. We compare our results with those produced by using simple Kmeans clustering on a real dataset and observe upto 10% absolute improvement in F1-scores. Through our experiments on synthetic dataset, we show that our algorithm gains more advantage over K-means algorithm when the data has large variance.

End-to-End Task-Completion Neural Dialogue Systems
Xiujun Li | Yun-Nung Chen | Lihong Li | Jianfeng Gao | Asli Celikyilmaz

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues.Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

End-to-end Network for Twitter Geolocation Prediction and Hashing
Jey Han Lau | Lianhua Chi | Khoi-Nguyen Tran | Trevor Cohn

We propose an end-to-end neural network to predict the geolocation of a tweet. The network takes as input a number of raw Twitter metadata such as the tweet message and associated user account information. Our model is language independent, and despite minimal feature engineering, it is interpretable and capable of learning location indicative words and timing patterns. Compared to state-of-the-art systems, our model outperforms them by 2%-6%. Additionally, we propose extensions to the model to compress representation learnt by the network into binary codes. Experiments show that it produces compact codes compared to benchmark hashing algorithms. An implementation of the model is released publicly.

Assessing the Verifiability of Attributions in News Text
Edward Newell | Ariane Schang | Drew Margolin | Derek Ruths

When reporting the news, journalists rely on the statements of stakeholders, experts, and officials. The attribution of such a statement is verifiable if its fidelity to the source can be confirmed or denied. In this paper, we develop a new NLP task: determining the verifiability of an attribution based on linguistic cues. We operationalize the notion of verifiability as a score between 0 and 1 using human judgments in a comparison-based approach. Using crowdsourcing, we create a dataset of verifiability-scored attributions, and demonstrate a model that achieves an RMSE of 0.057 and Spearman’s rank correlation of 0.95 to human-generated scores. We discuss the application of this technique to the analysis of mass media.

Domain Adaptation from User-level Facebook Models to County-level Twitter Predictions
Daniel Rieman | Kokil Jaidka | H. Andrew Schwartz | Lyle Ungar

Several studies have demonstrated how language models of user attributes, such as personality, can be built by using the Facebook language of social media users in conjunction with their responses to psychology questionnaires. It is challenging to apply these models to make general predictions about attributes of communities, such as personality distributions across US counties, because it requires 1. the potentially inavailability of the original training data because of privacy and ethical regulations, 2. adapting Facebook language models to Twitter language without retraining the model, and 3. adapting from users to county-level collections of tweets. We propose a two-step algorithm, Target Side Domain Adaptation (TSDA) for such domain adaptation when no labeled Twitter/county data is available. TSDA corrects for the different word distributions between Facebook and Twitter and for the varying word distributions across counties by adjusting target side word frequencies; no changes to the trained model are made. In the case of predicting the Big Five county-level personality traits, TSDA outperforms a state-of-the-art domain adaptation method, gives county-level predictions that have fewer extreme outliers, higher year-to-year stability, and higher correlation with county-level outcomes.

Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach
Lei Gao | Alexis Kuppersmith | Ruihong Huang

In the wake of a polarizing election, social media is laden with hateful content. To address various limitations of supervised hate speech classification methods including corpus bias and huge cost of annotation, we propose a weakly supervised two-path bootstrapping approach for an online hate speech detection model leveraging large-scale unlabeled data. This system significantly outperforms hate speech detection systems that are trained in a supervised manner using manually annotated data. Applying this model on a large quantity of tweets collected before, after, and on election day reveals motivations and patterns of inflammatory language.

Estimating Reactions and Recommending Products with Generative Models of Reviews
Jianmo Ni | Zachary C. Lipton | Sharad Vikram | Julian McAuley

Traditional approaches to recommendation focus on learning from large volumes of historical feedback to estimate simple numerical quantities (Will a user click on a product? Make a purchase? etc.). Natural language approaches that model information like product reviews have proved to be incredibly useful in improving the performance of such methods, as reviews provide valuable auxiliary information that can be used to better estimate latent user preferences and item properties. In this paper, rather than using reviews as an inputs to a recommender system, we focus on generating reviews as the model’s output. This requires us to efficiently model text (at the character level) to capture the preferences of the user, the properties of the item being consumed, and the interaction between them (i.e., the user’s preference). We show that this can model can be used to (a) generate plausible reviews and estimate nuanced reactions; (b) provide personalized rankings of existing reviews; and (c) recommend existing products more effectively.

Summarizing Lengthy Questions
Tatsuya Ishigaki | Hiroya Takamura | Manabu Okumura

In this research, we propose the task of question summarization. We first analyzed question-summary pairs extracted from a Community Question Answering (CQA) site, and found that a proportion of questions cannot be summarized by extractive approaches but requires abstractive approaches. We created a dataset by regarding the question-title pairs posted on the CQA site as question-summary pairs. By using the data, we trained extractive and abstractive summarization models, and compared them based on ROUGE scores and manual evaluations. Our experimental results show an abstractive method using an encoder-decoder model with a copying mechanism achieves better scores for both ROUGE-2 F-measure and the evaluations by human judges.

Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization
Tobias Falke | Christian M. Meyer | Iryna Gurevych

Concept-map-based multi-document summarization is a variant of traditional summarization that produces structured summaries in the form of concept maps. In this work, we propose a new model for the task that addresses several issues in previous methods. It learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming. It is also computationally more efficient than previous methods, allowing us to summarize larger document sets. We evaluate the model on two datasets, finding that it outperforms several approaches from previous work.

Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization
Litton J Kurisinkel | Yue Zhang | Vasudeva Varma

Existing work for abstractive multidocument summarization utilise existing phrase structures directly extracted from input documents to generate summary sentences. These methods can suffer from lack of consistence and coherence in merging phrases. We introduce a novel approach for abstractive multidocument summarization through partial dependency tree extraction, recombination and linearization. The method entrusts the summarizer to generate its own topically coherent sequential structures from scratch for effective communication. Results on TAC 2011, DUC-2004 and 2005 show that our system gives competitive results compared with state of the art abstractive summarization approaches in the literature. We also achieve competitive results in linguistic quality assessed by human evaluators.

Event Argument Identification on Dependency Graphs with Bidirectional LSTMs
Alex Judea | Michael Strube

In this paper we investigate the performance of event argument identification. We show that the performance is tied to syntactic complexity. Based on this finding, we propose a novel and effective system for event argument identification. Recurrent Neural Networks learn to produce meaningful representations of long and short dependency paths. Convolutional Neural Networks learn to decompose the lexical context of argument candidates. They are combined into a simple system which outperforms a feature-based, state-of-the-art event argument identifier without any manual feature engineering.

Selective Decoding for Cross-lingual Open Information Extraction
Sheng Zhang | Kevin Duh | Benjamin Van Durme

Cross-lingual open information extraction is the task of distilling facts from the source language into representations in the target language. We propose a novel encoder-decoder model for this problem. It employs a novel selective decoding mechanism, which explicitly models the sequence labeling process as well as the sequence generation process on the decoder side. Compared to a standard encoder-decoder model, selective decoding significantly increases the performance on a Chinese-English cross-lingual open IE dataset by 3.87-4.49 BLEU and 1.91-5.92 F1. We also extend our approach to low-resource scenarios, and gain promising improvement.

Event Ordering with a Generalized Model for Sieve Prediction Ranking
Bill McDowell | Nathanael Chambers | Alexander Ororbia II | David Reitter

This paper improves on several aspects of a sieve-based event ordering architecture, CAEVO (Chambers et al., 2014), which creates globally consistent temporal relations between events and time expressions. First, we examine the usage of word embeddings and semantic role features. With the incorporation of these new features, we demonstrate a 5% relative F1 gain over our replicated version of CAEVO. Second, we reformulate the architecture’s sieve-based inference algorithm as a prediction reranking method that approximately optimizes a scoring function computed using classifier precisions. Within this prediction reranking framework, we propose an alternative scoring function, showing an 8.8% relative gain over the original CAEVO. We further include an in-depth analysis of one of the main datasets that is used to evaluate temporal classifiers, and we show how despite using the densest corpus, there is still a danger of overfitting. While this paper focuses on temporal ordering, its results are applicable to other areas that use sieve-based architectures.

Open Relation Extraction and Grounding
Dian Yu | Lifu Huang | Heng Ji

Previous open Relation Extraction (open RE) approaches mainly rely on linguistic patterns and constraints to extract important relational triples from large-scale corpora. However, they lack of abilities to cover diverse relation expressions or measure the relative importance of candidate triples within a sentence. It is also challenging to name the relation type of a relational triple merely based on context words, which could limit the usefulness of open RE in downstream applications. We propose a novel importance-based open RE approach by exploiting the global structure of a dependency tree to extract salient triples. We design an unsupervised relation type naming method by grounding relational triples to a large-scale Knowledge Base (KB) schema, leveraging KB triples and weighted context words associated with relational triples. Experiments on the English Slot Filling 2013 dataset demonstrate that our approach achieves 8.1% higher F-score over state-of-the-art open RE methods.

Extraction of Gene-Environment Interaction from the Biomedical Literature
Jinseon You | Jin-Woo Chung | Wonsuk Yang | Jong C. Park

Genetic information in the literature has been extensively looked into for the purpose of discovering the etiology of a disease. As the gene-disease relation is sensitive to external factors, their identification is important to study a disease. Environmental influences, which are usually called Gene-Environment interaction (GxE), have been considered as important factors and have extensively been researched in biology. Nevertheless, there is still a lack of systems for automatic GxE extraction from the biomedical literature due to new challenges: (1) there are no preprocessing tools and corpora for GxE, (2) expressions of GxE are often quite implicit, and (3) document-level comprehension is usually required. We propose to overcome these challenges with neural network models and show that a modified sequence-to-sequence model with a static RNN decoder produces a good performance in GxE recognition.

Course Concept Extraction in MOOCs via Embedding-Based Graph Propagation
Liangming Pan | Xiaochen Wang | Chengjiang Li | Juanzi Li | Jie Tang

Massive Open Online Courses (MOOCs), offering a new way to study online, are revolutionizing education. One challenging issue in MOOCs is how to design effective and fine-grained course concepts such that students with different backgrounds can grasp the essence of the course. In this paper, we conduct a systematic investigation of the problem of course concept extraction for MOOCs. We propose to learn latent representations for candidate concepts via an embedding-based method. Moreover, we develop a graph-based propagation algorithm to rank the candidate concepts based on the learned representations. We evaluate the proposed method using different courses from XuetangX and Coursera. Experimental results show that our method significantly outperforms all the alternative methods (+0.013-0.318 in terms of R-precision; p<<0.01, t-test).

Identity Deception Detection
Verónica Pérez-Rosas | Quincy Davenport | Anna Mengdan Dai | Mohamed Abouelenien | Rada Mihalcea

This paper addresses the task of detecting identity deception in language. Using a novel identity deception dataset, consisting of real and portrayed identities from 600 individuals, we show that we can build accurate identity detectors targeting both age and gender, with accuracies of up to 88. We also perform an analysis of the linguistic patterns used in identity deception, which lead to interesting insights into identity portrayers.

Learning to Diagnose: Assimilating Clinical Narratives using Deep Reinforcement Learning
Yuan Ling | Sadid A. Hasan | Vivek Datla | Ashequl Qadir | Kathy Lee | Joey Liu | Oladimeji Farri

Clinical diagnosis is a critical and non-trivial aspect of patient care which often requires significant medical research and investigation based on an underlying clinical scenario. This paper proposes a novel approach by formulating clinical diagnosis as a reinforcement learning problem. During training, the reinforcement learning agent mimics the clinician’s cognitive process and learns the optimal policy to obtain the most appropriate diagnoses for a clinical narrative. This is achieved through an iterative search for candidate diagnoses from external knowledge sources via a sentence-by-sentence analysis of the inherent clinical context. A deep Q-network architecture is trained to optimize a reward function that measures the accuracy of the candidate diagnoses. Experiments on the TREC CDS datasets demonstrate the effectiveness of our system over various non-reinforcement learning-based systems.

Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
Florin Brad | Radu Cristian Alexandru Iacob | Ionel Alexandru Hosu | Traian Rebedea

Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouraging baseline results on a smaller manually annotated test corpus, obtained using an attention-based sequence-to-sequence neural network.

Acquisition and Assessment of Semantic Content for the Generation of Elaborateness and Indirectness in Spoken Dialogue Systems
Louisa Pragst | Koichiro Yoshino | Wolfgang Minker | Satoshi Nakamura | Stefan Ultes

In a dialogue system, the dialogue manager selects one of several system actions and thereby determines the system’s behaviour. Defining all possible system actions in a dialogue system by hand is a tedious work. While efforts have been made to automatically generate such system actions, those approaches are mostly focused on providing functional system behaviour. Adapting the system behaviour to the user becomes a difficult task due to the limited amount of system actions available. We aim to increase the adaptability of a dialogue system by automatically generating variants of system actions. In this work, we introduce an approach to automatically generate action variants for elaborateness and indirectness. Our proposed algorithm extracts RDF triplets from a knowledge base and rates their relevance to the original system action to find suitable content. We show that the results of our algorithm are mostly perceived similarly to human generated elaborateness and indirectness and can be used to adapt a conversation to the current user and situation. We also discuss where the results of our algorithm are still lacking and how this could be improved: Taking into account the conversation topic as well as the culture of the user is likely to have beneficial effect on the user’s perception.

Demographic Word Embeddings for Racism Detection on Twitter
Mohammed Hasanuzzaman | Gaël Dias | Andy Way

Most social media platforms grant users freedom of speech by allowing them to freely express their thoughts, beliefs, and opinions. Although this represents incredible and unique communication opportunities, it also presents important challenges. Online racism is such an example. In this study, we present a supervised learning strategy to detect racist language on Twitter based on word embedding that incorporate demographic (Age, Gender, and Location) information. Our methodology achieves reasonable classification accuracy over a gold standard dataset (F1=76.3%) and significantly improves over the classification performance of demographic-agnostic models.

Automatically Extracting Variant-Normalization Pairs for Japanese Text Normalization
Itsumi Saito | Kyosuke Nishida | Kugatsu Sadamitsu | Kuniko Saito | Junji Tomita

Social media texts, such as tweets from Twitter, contain many types of non-standard tokens, and the number of normalization approaches for handling such noisy text has been increasing. We present a method for automatically extracting pairs of a variant word and its normal form from unsegmented text on the basis of a pair-wise similarity approach. We incorporated the acquired variant-normalization pairs into Japanese morphological analysis. The experimental results show that our method can extract widely covered variants from large Twitter data and improve the recall of normalization without degrading the overall accuracy of Japanese morphological analysis.

Semantic Document Distance Measures and Unsupervised Document Revision Detection
Xiaofeng Zhu | Diego Klabjan | Patrick Bless

In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances. Furthermore, we propose two new document distance measures, word vector-based Dynamic Time Warping (wDTW) and word vector-based Tree Edit Distance (wTED). Our revision detection system is designed for a large scale corpus and implemented in Apache Spark. We demonstrate that our system can more precisely detect revisions than state-of-the-art methods by utilizing the Wikipedia revision dumps and simulated data sets.

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
Yelong Shen | Xiaodong Liu | Kevin Duh | Jianfeng Gao

Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning. Using a state-of-the-art RC model, we empirically investigate the performance of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets. The RC model is an end-to-end neural network with iterative attention, and uses reinforcement learning to dynamically control the number of turns. We find that multiple-turn reasoning outperforms single-turn reasoning for all question and answer types; further, we observe that enabling a flexible number of turns generally improves upon a fixed multiple-turn strategy. %across all question types, and is particularly beneficial to questions with lengthy, descriptive answers. We achieve results competitive to the state-of-the-art on these two datasets.

Automated Historical Fact-Checking by Passage Retrieval, Word Statistics, and Virtual Question-Answering
Mio Kobayashi | Ai Ishii | Chikara Hoshino | Hiroshi Miyashita | Takuya Matsuzaki

This paper presents a hybrid approach to the verification of statements about historical facts. The test data was collected from the world history examinations in a standardized achievement test for high school students. The data includes various kinds of false statements that were carefully written so as to deceive the students while they can be disproven on the basis of the teaching materials. Our system predicts the truth or falsehood of a statement based on text search, word cooccurrence statistics, factoid-style question answering, and temporal relation recognition. These features contribute to the judgement complementarily and achieved the state-of-the-art accuracy.

Integrating Subject, Type, and Property Identification for Simple Question Answering over Knowledge Base
Wei-Chuan Hsiao | Hen-Hsen Huang | Hsin-Hsi Chen

This paper presents an approach to identify subject, type and property from knowledge base (KB) for answering simple questions. We propose new features to rank entity candidates in KB. Besides, we split a relation in KB into type and property. Each of them is modeled by a bi-directional LSTM. Experimental results show that our model achieves the state-of-the-art performance on the SimpleQuestions dataset. The hard questions in the experiments are also analyzed in detail.

DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
Yanran Li | Hui Su | Xiaoyu Shen | Wenjie Li | Ziqiang Cao | Shuzi Niu

We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset reflect our daily communication way and cover various topics about our daily life. We also manually label the developed dataset with communication intention and emotion information. Then, we evaluate existing approaches on DailyDialog dataset and hope it benefit the research field of dialog systems. The dataset is available on

Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework
Aaron Steven White | Pushpendre Rastogi | Kevin Duh | Benjamin Van Durme

We propose to unify a variety of existing semantic classification tasks, such as semantic role labeling, anaphora resolution, and paraphrase detection, under the heading of Recognizing Textual Entailment (RTE). We present a general strategy to automatically generate one or more sentential hypotheses based on an input sentence and pre-existing manual semantic annotations. The resulting suite of datasets enables us to probe a statistical RTE model’s performance on different aspects of semantics. We demonstrate the value of this approach by investigating the behavior of a popular neural network RTE model.

Generating a Training Corpus for OCR Post-Correction Using Encoder-Decoder Model
Eva D’hondt | Cyril Grouin | Brigitte Grau

In this paper we present a novel approach to the automatic correction of OCR-induced orthographic errors in a given text. While current systems depend heavily on large training corpora or external information, such as domain-specific lexicons or confidence scores from the OCR process, our system only requires a small amount of (relatively) clean training data from a representative corpus to learn a character-based statistical language model using Bidirectional Long Short-Term Memory Networks (biLSTMs). We demonstrate the versatility and adaptability of our system on different text corpora with varying degrees of textual noise, including a real-life OCR corpus in the medical domain.

Multilingual Hierarchical Attention Networks for Document Classification
Nikolaos Pappas | Andrei Popescu-Belis

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging but potentially beneficial objective. To this end, we propose multilingual hierarchical attention networks for learning document structures, with shared encoders and/or shared attention mechanisms across languages, using multi-task learning and an aligned semantic space as input. We evaluate the proposed models on multilingual document classification with disjoint label sets, on a large dataset which we provide, with 600k news documents in 8 languages, and 5k labels. The multilingual models outperform monolingual ones in low-resource as well as full-resource settings, and use fewer parameters, thus confirming their computational efficiency and the utility of cross-language transfer.

Roles and Success in Wikipedia Talk Pages: Identifying Latent Patterns of Behavior
Keith Maki | Michael Yoder | Yohan Jo | Carolyn Rosé

In this work we investigate how role-based behavior profiles of a Wikipedia editor, considered against the backdrop of roles taken up by other editors in discussions, predict the success of the editor at achieving an impact on the associated article. We first contribute a new public dataset including a task predicting the success of Wikipedia editors involved in discussion, measured by an operationalization of the lasting impact of their edits in the article. We then propose a probabilistic graphical model that advances earlier work inducing latent discussion roles using the light supervision of success in the negotiation task. We evaluate the performance of the model and interpret findings of roles and group configurations that lead to certain outcomes on Wikipedia.


pdf (full)
bib (full)
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

pdf bib
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Greg Kondrak | Taro Watanabe

pdf bib
CKY-based Convolutional Attention for Neural Machine Translation
Taiki Watanabe | Akihiro Tamura | Takashi Ninomiya

This paper proposes a new attention mechanism for neural machine translation (NMT) based on convolutional neural networks (CNNs), which is inspired by the CKY algorithm. The proposed attention represents every possible combination of source words (e.g., phrases and structures) through CNNs, which imitates the CKY table in the algorithm. NMT, incorporating the proposed attention, decodes a target sentence on the basis of the attention scores of the hidden states of CNNs. The proposed attention enables NMT to capture alignments from underlying structures of a source sentence without sentence parsing. The evaluations on the Asian Scientific Paper Excerpt Corpus (ASPEC) English-Japanese translation task show that the proposed attention gains 0.66 points in BLEU.

pdf bib
Supervised Attention for Sequence-to-Sequence Constituency Parsing
Hidetaka Kamigaito | Katsuhiko Hayashi | Tsutomu Hirao | Hiroya Takamura | Manabu Okumura | Masaaki Nagata

The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT). Recently, MT performances were improved by incorporating supervised attention into the model. In this paper, we introduce supervised attention to constituency parsing that can be regarded as another translation task. Evaluation results on the PTB corpus showed that the bracketing F-measure was improved by supervised attention.

Transferring Semantic Roles Using Translation and Syntactic Information
Maryam Aminian | Mohammad Sadegh Rasooli | Mona Diab

Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data. We propose a transfer method that employs information from source and target syntactic dependencies as well as word alignment density to improve the quality of an iterative bootstrapping method. Our experiments yield a 3.5 absolute labeled F-score improvement over a standard annotation projection method.

Neural Lattice Search for Domain Adaptation in Machine Translation
Huda Khayrallah | Gaurav Kumar | Kevin Duh | Matt Post | Philipp Koehn

Domain adaptation is a major challenge for neural machine translation (NMT). Given unknown words or new domains, NMT systems tend to generate fluent translations at the expense of adequacy. We present a stack-based lattice search algorithm for NMT and show that constraining its search space with lattices generated by phrase-based machine translation (PBMT) improves robustness. We report consistent BLEU score gains across four diverse domain adaptation tasks involving medical, IT, Koran, or subtitles texts.

Analyzing Well-Formedness of Syllables in Japanese Sign Language
Satoshi Yawata | Makoto Miwa | Yutaka Sasaki | Daisuke Hara

This paper tackles a problem of analyzing the well-formedness of syllables in Japanese Sign Language (JSL). We formulate the problem as a classification problem that classifies syllables into well-formed or ill-formed. We build a data set that contains hand-coded syllables and their well-formedness. We define a fine-grained feature set based on the hand-coded syllables and train a logistic regression classifier on labeled syllables, expecting to find the discriminative features from the trained classifier. We also perform pseudo active learning to investigate the applicability of active learning in analyzing syllables. In the experiments, the best classifier with our combinatorial features achieved the accuracy of 87.0%. The pseudo active learning is also shown to be effective showing that it could reduce about 84% of training instances to achieve the accuracy of 82.0% when compared to the model without active learning.

Towards Lower Bounds on Number of Dimensions for Word Embeddings
Kevin Patel | Pushpak Bhattacharyya

Word embeddings are a relatively new addition to the modern NLP researcher’s toolkit. However, unlike other tools, word embeddings are used in a black box manner. There are very few studies regarding various hyperparameters. One such hyperparameter is the dimension of word embeddings. They are rather decided based on a rule of thumb: in the range 50 to 300. In this paper, we show that the dimension should instead be chosen based on corpus statistics. More specifically, we show that the number of pairwise equidistant words of the corpus vocabulary (as defined by some distance/similarity metric) gives a lower bound on the the number of dimensions , and going below this bound results in degradation of quality of learned word embeddings. Through our evaluations on standard word embedding evaluation tasks, we show that for dimensions higher than or equal to the bound, we get better results as compared to the ones below it.

Sequence to Sequence Learning for Event Prediction
Dai Quoc Nguyen | Dat Quoc Nguyen | Cuong Xuan Chu | Stefan Thater | Manfred Pinkal

This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively. Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events.

Input-to-Output Gate to Improve RNN Language Models
Sho Takase | Jun Suzuki | Masaaki Nagata

This paper proposes a reinforcing method that refines the output layers of existing Recurrent Neural Network (RNN) language models. We refer to our proposed method as Input-to-Output Gate (IOG). IOG has an extremely simple structure, and thus, can be easily combined with any RNN language models. Our experiments on the Penn Treebank and WikiText-2 datasets demonstrate that IOG consistently boosts the performance of several different types of current topline RNN language models.

Counterfactual Language Model Adaptation for Suggesting Phrases
Kenneth Arnold | Kai-Wei Chang | Adam Kalai

Mobile devices use language models to suggest words and phrases for use in text entry. Traditional language models are based on contextual word frequency in a static corpus of text. However, certain types of phrases, when offered to writers as suggestions, may be systematically chosen more often than their frequency would predict. In this paper, we propose the task of generating suggestions that writers accept, a related but distinct task to making accurate predictions. Although this task is fundamentally interactive, we propose a counterfactual setting that permits offline training and evaluation. We find that even a simple language model can capture text characteristics that improve acceptability.

Deep Automated Multi-task Learning
Davis Liang | Yan Shu

Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as secondary tasks in an MTL model. We explore next word prediction, next character prediction, and missing word completion as potential automated tasks. Our results show that training on a primary task in parallel with a secondary automated task improves both the convergence speed and accuracy for the primary task. We suggest two methods for augmenting an existing network with automated tasks and establish better performance in topic prediction, sentiment analysis, and hashtag recommendation. Finally, we show that the MTL models can perform well on datasets that are small and colloquial by nature.

Post-Processing Techniques for Improving Predictions of Multilabel Learning Approaches
Akshay Soni | Aasish Pappu | Jerry Chia-mau Ni | Troy Chevalier

In Multilabel Learning (MLL) each training instance is associated with a set of labels and the task is to learn a function that maps an unseen instance to its corresponding label set. In this paper, we present a suite of – MLL algorithm independent – post-processing techniques that utilize the conditional and directional label-dependences in order to make the predictions from any MLL approach more coherent and precise. We solve constraint optimization problem over the output produced by any MLL approach and the result is a refined version of the input predicted label set. Using proposed techniques, we show absolute improvement of 3% on English News and 10% on Chinese E-commerce datasets for P@K metric.

Learning Kernels over Strings using Gaussian Processes
Daniel Beck | Trevor Cohn

Non-contiguous word sequences are widely known to be important in modelling natural language. However they not explicitly encoded in common text representations. In this work we propose a model for text processing using string kernels, capable of flexibly representing non-contiguous sequences. Specifically, we derive a vectorised version of the string kernel algorithm and their gradients, allowing efficient hyperparameter optimisation as part of a Gaussian Process framework. Experiments on synthetic data and text regression for emotion analysis show the promise of this technique.

Substring Frequency Features for Segmentation of Japanese Katakana Words with Unlabeled Corpora
Yoshinari Fujinuma | Alvin Grissom II

Word segmentation is crucial in natural language processing tasks for unsegmented languages. In Japanese, many out-of-vocabulary words appear in the phonetic syllabary katakana, making segmentation more difficult due to the lack of clues found in mixed script settings. In this paper, we propose a straightforward approach based on a variant of tf-idf and apply it to the problem of word segmentation in Japanese. Even though our method uses only an unlabeled corpus, experimental results show that it achieves performance comparable to existing methods that use manually labeled corpora. Furthermore, it improves performance of simple word segmentation models trained on a manually labeled corpus.

MONPA: Multi-objective Named-entity and Part-of-speech Annotator for Chinese using Recurrent Neural Network
Yu-Lun Hsieh | Yung-Chun Chang | Yi-Jie Huang | Shu-Hao Yeh | Chun-Hung Chen | Wen-Lian Hsu

Part-of-speech (POS) tagging and named entity recognition (NER) are crucial steps in natural language processing. In addition, the difficulty of word segmentation places additional burden on those who intend to deal with languages such as Chinese, and pipelined systems often suffer from error propagation. This work proposes an end-to-end model using character-based recurrent neural network (RNN) to jointly accomplish segmentation, POS tagging and NER of a Chinese sentence. Experiments on previous word segmentation and NER datasets show that a single model with the proposed architecture is comparable to those trained specifically for each task, and outperforms freely-available softwares. Moreover, we provide a web-based interface for the public to easily access this resource.

Recall is the Proper Evaluation Metric for Word Segmentation
Yan Shao | Christian Hardmeier | Joakim Nivre

We extensively analyse the correlations and drawbacks of conventionally employed evaluation metrics for word segmentation. Unlike in standard information retrieval, precision favours under-splitting systems and therefore can be misleading in word segmentation. Overall, based on both theoretical and experimental analysis, we propose that precision should be excluded from the standard evaluation metrics and that the evaluation score obtained by using only recall is sufficient and better correlated with the performance of word segmentation systems.

Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields
Ryan Cotterell | Kevin Duh

Low-resource named entity recognition is still an open problem in NLP. Most state-of-the-art systems require tens of thousands of annotated sentences in order to obtain high performance. However, for most of the world’s languages it is unfeasible to obtain such annotation. In this paper, we present a transfer learning scheme, whereby we train character-level neural CRFs to predict named entities for both high-resource languages and low-resource languages jointly. Learning character representations for multiple related languages allows knowledge transfer from the high-resource languages to the low-resource ones, improving F1 by up to 9.8 points.

Segment-Level Neural Conditional Random Fields for Named Entity Recognition
Motoki Sato | Hiroyuki Shindo | Ikuya Yamada | Yuji Matsumoto

We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking. Our segment-level CRF can consider higher-order label dependencies compared with conventional word-level CRF. Since it is difficult to consider all possible variable length segments, our method uses segment lattice constructed from the word-level tagging model to reduce the search space. Performing experiments on NER and chunking, we demonstrate that our method outperforms conventional word-level CRF with neural networks.

Integrating Vision and Language Datasets to Measure Word Concreteness
Gitit Kehat | James Pustejovsky

We present and take advantage of the inherent visualizability properties of words in visual corpora (the textual components of vision-language datasets) to compute concreteness scores for words. Our simple method does not require hand-annotated concreteness score lists for training, and yields state-of-the-art results when evaluated against concreteness scores lists and previously derived scores, as well as when used for metaphor detection.

Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification
Tomoyuki Kajiwara | Atsushi Fujita

This paper examines the usefulness of semantic features based on word alignments for estimating the quality of text simplification. Specifically, we introduce seven types of alignment-based features computed on the basis of word embeddings and paraphrase lexicons. Through an empirical experiment using the QATS dataset, we confirm that we can achieve the state-of-the-art performance only with these features.

Injecting Word Embeddings with Another Language’s Resource : An Application of Bilingual Embeddings
Prakhar Pandey | Vikram Pudi | Manish Shrivastava

Word embeddings learned from text corpus can be improved by injecting knowledge from external resources, while at the same time also specializing them for similarity or relatedness. These knowledge resources (like WordNet, Paraphrase Database) may not exist for all languages. In this work we introduce a method to inject word embeddings of a language with knowledge resource of another language by leveraging bilingual embeddings. First we improve word embeddings of German, Italian, French and Spanish using resources of English and test them on variety of word similarity tasks. Then we demonstrate the utility of our method by creating improved embeddings for Urdu and Telugu languages using Hindi WordNet, beating the previously established baseline for Urdu.

Improving Black-box Speech Recognition using Semantic Parsing
Rodolfo Corona | Jesse Thomason | Raymond Mooney

Speech is a natural channel for human-computer interaction in robotics and consumer applications. Natural language understanding pipelines that start with speech can have trouble recovering from speech recognition errors. Black-box automatic speech recognition (ASR) systems, built for general purpose use, are unable to take advantage of in-domain language models that could otherwise ameliorate these errors. In this work, we present a method for re-ranking black-box ASR hypotheses using an in-domain language model and semantic parser trained for a particular task. Our re-ranking method significantly improves both transcription accuracy and semantic understanding over a state-of-the-art ASR’s vanilla output.

Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis
Yuichiroh Matsubayashi | Kentaro Inui

The research trend in Japanese predicate-argument structure (PAS) analysis is shifting from pointwise prediction models with local features to global models designed to search for globally optimal solutions. However, the existing global models tend to employ only relatively simple local features; therefore, the overall performance gains are rather limited. The importance of designing a local model is demonstrated in this study by showing that the performance of a sophisticated local model can be considerably improved with recent feature embedding methods and a feature combination learning based on a neural network, outperforming the state-of-the-art global models in F1 on a common benchmark dataset.

Natural Language Informs the Interpretation of Iconic Gestures: A Computational Approach
Ting Han | Julian Hough | David Schlangen

When giving descriptions, speakers often signify object shape or size with hand gestures. Such so-called ‘iconic’ gestures represent their meaning through their relevance to referents in the verbal content, rather than having a conventional form. The gesture form on its own is often ambiguous, and the aspect of the referent that it highlights is constrained by what the language makes salient. We show how the verbal content guides gesture interpretation through a computational model that frames the task as a multi-label classification task that maps multimodal utterances to semantic categories, using annotated human-human data.

Modelling Representation Noise in Emotion Analysis using Gaussian Processes
Daniel Beck

Emotion Analysis is the task of modelling latent emotions present in natural language. Labelled datasets for this task are scarce so learning good input text representations is not trivial. Using averaged word embeddings is a simple way to leverage unlabelled corpora to build text representations but this approach can be prone to noise either coming from the embedding themselves or the averaging procedure. In this paper we propose a model for Emotion Analysis using Gaussian Processes and kernels that are better suitable for functions that exhibit noisy behaviour. Empirical evaluations in a emotion prediction task show that our model outperforms commonly used baselines for regression.

Are Manually Prepared Affective Lexicons Really Useful for Sentiment Analysis
Minglei Li | Qin Lu | Yunfei Long

In this paper, we investigate the effectiveness of different affective lexicons through sentiment analysis of phrases. We examine how phrases can be represented through manually prepared lexicons, extended lexicons using computational methods, or word embedding. Comparative studies clearly show that word embedding using unsupervised distributional method outperforms manually prepared lexicons no matter what affective models are used in the lexicons. Our conclusion is that although different affective lexicons are cognitively backed by theories, they do not show any advantage over the automatically obtained word embedding.

MTNA: A Neural Multi-task Model for Aspect Category Classification and Aspect Term Extraction On Restaurant Reviews
Wei Xue | Wubai Zhou | Tao Li | Qing Wang

Online reviews are valuable resources not only for consumers to make decisions before purchase, but also for providers to get feedbacks for their services or commodities. In Aspect Based Sentiment Analysis (ABSA), it is critical to identify aspect categories and extract aspect terms from the sentences of user-generated reviews. However, the two tasks are often treated independently, even though they are closely related. Intuitively, the learned knowledge of one task should inform the other learning task. In this paper, we propose a multi-task learning model based on neural networks to solve them together. We demonstrate the improved performance of our multi-task learning model over the models trained separately on three public dataset released by SemEval workshops.

Can Discourse Relations be Identified Incrementally?
Frances Yung | Hiroshi Noji | Yuji Matsumoto

Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived. Inspired by this cognitive ability, incremental algorithms for natural language processing tasks have been proposed and demonstrated promising performance. For discourse relation (DR) parsing, however, it is not yet clear to what extent humans can recognize DRs incrementally, because the latent ‘nodes’ of discourse structure can span clauses and sentences. To answer this question, this work investigates incrementality in discourse processing based on a corpus annotated with DR signals. We find that DRs are dominantly signaled at the boundary between the two constituent discourse units. The findings complement existing psycholinguistic theories on expectation in discourse processing and provide direction for incremental discourse parsing.

Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning
Ta-Chung Chi | Po-Chun Chen | Shang-Yu Su | Yun-Nung Chen

Language understanding (LU) and dialogue policy learning are two essential components in conversational systems. Human-human dialogues are not well-controlled and often random and unpredictable due to their own goals and speaking habits. This paper proposes a role-based contextual model to consider different speaker roles independently based on the various speaking patterns in the multi-turn dialogues. The experiments on the benchmark dataset show that the proposed role-based model successfully learns role-specific behavioral patterns for contextual encoding and then significantly improves language understanding and dialogue policy learning tasks.

Diversifying Neural Conversation Model with Maximal Marginal Relevance
Yiping Song | Zhiliang Tian | Dongyan Zhao | Ming Zhang | Rui Yan

Neural conversation systems, typically using sequence-to-sequence (seq2seq) models, are showing promising progress recently. However, traditional seq2seq suffer from a severe weakness: during beam search decoding, they tend to rank universal replies at the top of the candidate list, resulting in the lack of diversity among candidate replies. Maximum Marginal Relevance (MMR) is a ranking algorithm that has been widely used for subset selection. In this paper, we propose the MMR-BS decoding method, which incorporates MMR into the beam search (BS) process of seq2seq. The MMR-BS method improves the diversity of generated replies without sacrificing their high relevance with the user-issued query. Experiments show that our proposed model achieves the best performance among other comparison methods.

Dialog for Language to Code
Shobhit Chaurasia | Raymond J. Mooney

Generating computer code from natural language descriptions has been a long-standing problem. Prior work in this domain has restricted itself to generating code in one shot from a single description. To overcome this limitation, we propose a system that can engage users in a dialog to clarify their intent until it has all the information to produce correct code. To evaluate the efficacy of dialog in code generation, we focus on synthesizing conditional statements in the form of IFTTT recipes.

Using Analytic Scoring Rubrics in the Automatic Assessment of College-Level Summary Writing Tasks in L2
Tamara Sladoljev-Agejev | Jan Šnajder

Assessing summaries is a demanding, yet useful task which provides valuable information on language competence, especially for second language learners. We consider automated scoring of college-level summary writing task in English as a second language (EL2). We adopt the Reading-for-Understanding (RU) cognitive framework, extended with the Reading-to-Write (RW) element, and use analytic scoring with six rubrics covering content and writing quality. We show that regression models with reference-based and linguistic features considerably outperform the baselines across all the rubrics. Moreover, we find interesting correlations between summary features and analytic rubrics, revealing the links between the RU and RW constructs.

A Statistical Framework for Product Description Generation
Jinpeng Wang | Yutai Hou | Jing Liu | Yunbo Cao | Chin-Yew Lin

We present in this paper a statistical framework that generates accurate and fluent product description from product attributes. Specifically, after extracting templates and learning writing knowledge from attribute-description parallel data, we use the learned knowledge to decide what to say and how to say for product description generation. To evaluate accuracy and fluency for the generated descriptions, in addition to BLEU and Recall, we propose to measure what to say (in terms of attribute coverage) and to measure how to say (by attribute-specified generation) separately. Experimental results show that our framework is effective.

Automatic Text Summarization Using Reinforcement Learning with Embedding Features
Gyoung Ho Lee | Kong Joo Lee

An automatic text summarization system can automatically generate a short and brief summary that contains a main concept of an original document. In this work, we explore the advantages of simple embedding features in Reinforcement leaning approach to automatic text summarization tasks. In addition, we propose a novel deep learning network for estimating Q-values used in Reinforcement learning. We evaluate our model by using ROUGE scores with DUC 2001, 2002, Wikipedia, ACL-ARC data. Evaluation results show that our model is competitive with the previous models.

SSAS: Semantic Similarity for Abstractive Summarization
Raghuram Vadapalli | Litton J Kurisinkel | Manish Gupta | Vasudeva Varma

Ideally a metric evaluating an abstract system summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a human-written reference summary. Most of the previous approaches relied upon word or syntactic sub-sequence overlap to evaluate system-generated summaries. Such metrics cannot evaluate the summary at semantic inference level. Through this work we introduce the metric of Semantic Similarity for Abstractive Summarization (SSAS), which leverages natural language inference and paraphrasing techniques to frame a novel approach to evaluate system summaries at semantic inference level. SSAS is based upon a weighted composition of quantities representing the level of agreement, contradiction, independence, paraphrasing, and optionally ROUGE score between a system-generated and a human-written summary.

Taking into account Inter-sentence Similarity for Update Summarization
Maâli Mnasri | Gaël de Chalendar | Olivier Ferret

Following Gillick and Favre (2009), a lot of work about extractive summarization has modeled this task by associating two contrary constraints: one aims at maximizing the coverage of the summary with respect to its information content while the other represents its size limit. In this context, the notion of redundancy is only implicitly taken into account. In this article, we extend the framework defined by Gillick and Favre (2009) by examining how and to what extent integrating semantic sentence similarity into an update summarization system can improve its results. We show more precisely the impact of this strategy through evaluations performed on DUC 2007 and TAC 2008 and 2009 datasets.

Hyperspherical Query Likelihood Models with Word Embeddings
Ryo Masumura | Taichi Asami | Hirokazu Masataki | Kugatsu Sadamitsu | Kyosuke Nishida | Ryuichiro Higashinaka

This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, key idea is to directly leverage the word embeddings as random variables for directional probabilistic models based on von Mises-Fisher distributions which are familiar to cosine distances. The proposed method enables us to theoretically take semantic similarities between document and target queries into consideration without introducing heuristic expansion techniques. In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs. Experiments show document retrieval evaluation results in which a hyperspherical QLM is compared to conventional QLMs and document distance metrics using word or document embeddings.

Dual Constrained Question Embeddings with Relational Knowledge Bases for Simple Question Answering
Kaustubh Kulkarni | Riku Togashi | Hideyuki Maeda | Sumio Fujita

Embedding based approaches are shown to be effective for solving simple Question Answering (QA) problems in recent works. The major drawback of current approaches is that they look only at the similarity (constraint) between a question and a head, relation pair. Due to the absence of tail (answer) in the questions, these models often require paraphrase datasets to obtain adequate embeddings. In this paper, we propose a dual constraint model which exploits the embeddings obtained by Trans* family of algorithms to solve the simple QA problem without using any additional resources such as paraphrase datasets. The results obtained prove that the embeddings learned using dual constraints are better than those with single constraint models having similar architecture.

Efficiency-aware Answering of Compositional Questions using Answer Type Prediction
David Ziegler | Abdalghani Abujabal | Rishiraj Saha Roy | Gerhard Weikum

This paper investigates the problem of answering compositional factoid questions over knowledge bases (KB) under efficiency constraints. The method, called TIPI, (i) decomposes compositional questions, (ii) predicts answer types for individual sub-questions, (iii) reasons over the compatibility of joint types, and finally, (iv) formulates compositional SPARQL queries respecting type constraints. TIPI’s answer type predictor is trained using distant supervision, and exploits lexical, syntactic and embedding-based features to compute context- and hierarchy-aware candidate answer types for an input question. Experiments on a recent benchmark show that TIPI results in state-of-the-art performance under the real-world assumption that only a single SPARQL query can be executed over the KB, and substantial reduction in the number of queries in the more general case.

High Recall Open IE for Relation Discovery
Hady Elsahar | Christophe Gravier | Frederique Laforest

Relation Discovery discovers predicates (relation types) from a text corpus relying on the co-occurrence of two named entities in the same sentence. This is a very narrowing constraint: it represents only a small fraction of all relation mentions in practice. In this paper we propose a high recall approach for Open IE, which enables covering up to 16 times more sentences in a large corpus. Comparison against OpenIE systems shows that our proposed approach achieves 28% improvement over the highest recall OpenIE system and 6% improvement in precision than the same system.

Using Context Events in Neural Network Models for Event Temporal Status Identification
Zeyu Dai | Wenlin Yao | Ruihong Huang

Focusing on the task of identifying event temporal status, we find that events directly or indirectly governing the target event in a dependency tree are most important contexts. Therefore, we extract dependency chains containing context events and use them as input in neural network models, which consistently outperform previous models using local context words as input. Visualization verifies that the dependency chain representation can effectively capture the context events which are closely related to the target event and play key roles in predicting event temporal status.

Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory
Yu-Lun Hsieh | Yung-Chun Chang | Nai-Wen Chang | Wen-Lian Hsu

In this paper, we propose a recurrent neural network model for identifying protein-protein interactions in biomedical literature. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that our approach significantly surpasses state-of-the-art methods with relative improvements of 10% and 18%, respectively. Cross-corpus evaluation also demonstrate that the proposed model remains robust despite using different training data. These results suggest that RNN can effectively capture semantic relationships among proteins as well as generalizes over different corpora, without any feature engineering.

Identifying Empathetic Messages in Online Health Communities
Hamed Khanpour | Cornelia Caragea | Prakhar Biyani

Empathy captures one’s ability to correlate with and understand others’ emotional states and experiences. Messages with empathetic content are considered as one of the main advantages for joining online health communities due to their potential to improve people’s moods. Unfortunately, to this date, no computational studies exist that automatically identify empathetic messages in online health communities. We propose a combination of Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks, and show that the proposed model outperforms each individual model (CNN and LSTM) as well as several baselines.

Fake News Detection Through Multi-Perspective Speaker Profiles
Yunfei Long | Qin Lu | Rong Xiang | Minglei Li | Chu-Ren Huang

Automatic fake news detection is an important, yet very challenging topic. Traditional methods using lexical features have only very limited success. This paper proposes a novel method to incorporate speaker profiles into an attention based LSTM model for fake news detection. Speaker profiles contribute to the model in two ways. One is to include them in the attention model. The other includes them as additional input data. By adding speaker profiles such as party affiliation, speaker title, location and credit history, our model outperforms the state-of-the-art method by 14.5% in accuracy using a benchmark fake news detection dataset. This proves that speaker profiles provide valuable information to validate the credibility of news articles.

Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
Itsumi Saito | Jun Suzuki | Kyosuke Nishida | Kugatsu Sadamitsu | Satoshi Kobashikawa | Ryo Masumura | Yuji Matsumoto | Junji Tomita

In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. % such as machine translation or machine summarization. In general, we have to prepare for a large amount of training data to train an encoder-decoder model. Unlike machine translation, there are few training data for text-normalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.

Using Social Networks to Improve Language Variety Identification with Neural Networks
Yasuhide Miura | Tomoki Taniguchi | Motoki Taniguchi | Shotaro Misawa | Tomoko Ohkuma

We propose a hierarchical neural network model for language variety identification that integrates information from a social network. Recently, language variety identification has enjoyed heightened popularity as an advanced task of language identification. The proposed model uses additional texts from a social network to improve language variety identification from two perspectives. First, they are used to introduce the effects of homophily. Secondly, they are used as expanded training data for shared layers of the proposed model. By introducing information from social networks, the model improved its accuracy by 1.67-5.56. Compared to state-of-the-art baselines, these improved performances are better in English and comparable in Spanish. Furthermore, we analyzed the cases of Portuguese and Arabic when the model showed weak performances, and found that the effect of homophily is likely to be weak due to sparsity and noises compared to languages with the strong performances.

Boosting Neural Machine Translation
Dakun Zhang | Jungi Kim | Josep Crego | Jean Senellart

Training efficiency is one of the main problems for Neural Machine Translation (NMT). Deep networks need for very large data as well as many training iterations to achieve state-of-the-art performance. This results in very high computation cost, slowing down research and industrialisation. In this paper, we propose to alleviate this problem with several training methods based on data boosting and bootstrap with no modifications to the neural network. It imitates the learning process of humans, which typically spend more time when learning “difficult” concepts than easier ones. We experiment on an English-French translation task showing accuracy improvements of up to 1.63 BLEU while saving 20% of training time.

Improving Japanese-to-English Neural Machine Translation by Voice Prediction
Hayahide Yamagishi | Shin Kanouchi | Takayuki Sato | Mamoru Komachi

This study reports an attempt to predict the voice of reference using the information from the input sentences or previous input/output sentences. Our previous study presented a voice controlling method to generate sentences for neural machine translation, wherein it was demonstrated that the BLEU score improved when the voice of generated sentence was controlled relative to that of the reference. However, it is impractical to use the reference information because we cannot discern the voice of the correct translation in advance. Thus, this study presents a voice prediction method for generated sentences for neural machine translation. While evaluating on Japanese-to-English translation, we obtain a 0.70-improvement in the BLEU using the predicted voice.

Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT
Anoop Kunchukuttan | Maulik Shah | Pradyot Prakash | Pushpak Bhattacharyya

We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages can compensate for the lack of a direct parallel corpus.

Key-value Attention Mechanism for Neural Machine Translation
Hideya Mino | Masao Utiyama | Eiichiro Sumita | Takenobu Tokunaga

In this paper, we propose a neural machine translation (NMT) with a key-value attention mechanism on the source-side encoder. The key-value attention mechanism separates the source-side content vector into two types of memory known as the key and the value. The key is used for calculating the attention distribution, and the value is used for encoding the context representation. Experiments on three different tasks indicate that our model outperforms an NMT model with a conventional attention mechanism. Furthermore, we perform experiments with a conventional NMT framework, in which a part of the initial value of a weight matrix is set to zero so that the matrix is as the same initial-state as the key-value attention mechanism. As a result, we obtain comparable results with the key-value attention mechanism without changing the network structure.

Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation
Toan Q. Nguyen | David Chiang

We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair. The method is based on the transfer method of Zoph et al., but whereas their method ignores any source vocabulary overlap, ours exploits it. First, we split words using Byte Pair Encoding (BPE) to increase vocabulary overlap. Then, we train a model on the first language pair and transfer its parameters, including its source word embeddings, to another model and continue training on the second language pair. Our experiments show that transfer learning helps word-based translation only slightly, but when used on top of a much stronger BPE baseline, it yields larger improvements of up to 4.3 BLEU.

Concept Equalization to Guide Correct Training of Neural Machine Translation
Kangil Kim | Jong-Hun Shin | Seung-Hoon Na | SangKeun Jung

Neural machine translation decoders are usually conditional language models to sequentially generate words for target sentences. This approach is limited to find the best word composition and requires help of explicit methods as beam search. To help learning correct compositional mechanisms in NMTs, we propose concept equalization using direct mapping distributed representations of source and target sentences. In a translation experiment from English to French, the concept equalization significantly improved translation quality by 3.00 BLEU points compared to a state-of-the-art NMT model.

PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
Franck Dernoncourt | Ji Young Lee

We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasing a new large dataset will help develop more accurate algorithms for this task. Second, from an application perspective, researchers need better tools to efficiently skim through the literature. Automatically classifying each sentence in an abstract would help researchers read abstracts more efficiently, especially in fields where abstracts may be long, such as the medical field.

A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation
Antonio Valerio Miceli Barone | Rico Sennrich

Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest. Progress in these areas has been limited by the low availability of parallel corpora of code and natural language descriptions, which tend to be small and constrained to specific domains. In this work we introduce a large and diverse parallel corpus of a hundred thousands Python functions with their documentation strings (“docstrings”) generated by scraping open source repositories on GitHub. We describe baseline results for the code documentation and code generation tasks obtained by neural machine translation. We also experiment with data augmentation techniques to further increase the amount of training data. We release our datasets and processing scripts in order to stimulate research in these areas.

Building Large Chinese Corpus for Spoken Dialogue Research in Specific Domains
Changliang Li | Xiuying Wang

Corpus is a valuable resource for information retrieval and data-driven natural language processing systems,especially for spoken dialogue research in specific domains. However,there is little non-English corpora, particular for ones in Chinese. Spoken by the nation with the largest population in the world, Chinese become increasingly prevalent and popular among millions of people worldwide. In this paper, we build a large-scale and high-quality Chinese corpus, called CSDC (Chinese Spoken Dialogue Corpus). It contains five domains and more than 140 thousand dialogues in all. Each sentence in this corpus is annotated with slot information additionally compared to other corpora. To our best knowledge, this is the largest Chinese spoken dialogue corpus, as well as the first one with slot information. With this corpus, we proposed a method and did a well-designed experiment. The indicative result is reported at last.

Identifying Speakers and Listeners of Quoted Speech in Literary Works
Chak Yan Yeung | John Lee

We present the first study that evaluates both speaker and listener identification for direct speech in literary texts. Our approach consists of two steps: identification of speakers and listeners near the quotes, and dialogue chain segmentation. Evaluation results show that this approach outperforms a rule-based approach that is state-of-the-art on a corpus of literary texts.

Language-Independent Prediction of Psycholinguistic Properties of Words
Yo Ehara

The psycholinguistic properties of words, namely, word familiarity, age of acquisition, concreteness, and imagery, have been reported to be effective for educational natural language-processing tasks. Previous studies on predicting the values of these properties rely on language-dependent features. This paper is the first to propose a practical language-independent method for predicting such values by using only a large raw corpus in a language. Through experiments, our method successfully predicted the values of these properties in two languages. The results for English were competitive with the reported accuracy achieved using features specific to English.

Correlation Analysis of Chronic Obstructive Pulmonary Disease (COPD) and its Biomarkers Using the Word Embeddings
Byeong-Hun Yoon | Yu-Seop Kim

It is very costly and time consuming to find new biomarkers for specific diseases in clinical laboratories. In this study, to find new biomarkers most closely related to Chronic Obstructive Pulmonary Disease (COPD), which is widely known as respiratory disease, biomarkers known to be associated with respiratory diseases and COPD itself were converted into word embedding. And their similarities were measured. We used Word2Vec, Canonical Correlation Analysis (CCA), and Global Vector (GloVe) for word embedding. In order to replace the clinical evaluation, the titles and abstracts of papers retrieved from Google Scholars were analyzed and quantified to estimate the performance of the word em-bedding models.

Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems
Hiroki Asano | Tomoya Mizumoto | Kentaro Inui

In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage. To address this problem, a reference-less approach has recently emerged; however, previous reference-less metrics that only consider the criterion of grammaticality, have not worked as well as reference-based metrics. This study explores the potential of extending a prior grammaticality-based method to establish a reference-less evaluation method for GEC systems. Further, we empirically show that a reference-less metric that combines fluency and meaning preservation with grammaticality provides a better estimate of manual scores than that of commonly used reference-based metrics. To our knowledge, this is the first study that provides empirical evidence that a reference-less metric can replace reference-based metrics in evaluating GEC systems.

CVBed: Structuring CVs usingWord Embeddings
Shweta Garg | Sudhanshu S Singh | Abhijit Mishra | Kuntal Dey

Automatic analysis of curriculum vitae (CVs) of applicants is of tremendous importance in recruitment scenarios. The semi-structuredness of CVs, however, makes CV processing a challenging task. We propose a solution towards transforming CVs to follow a unified structure, thereby, paving ways for smoother CV analysis. The problem of restructuring is posed as a section relabeling problem, where each section of a given CV gets reassigned to a predefined label. Our relabeling method relies on semantic relatedness computed between section header, content and labels, based on phrase-embeddings learned from a large pool of CVs. We follow different heuristics to measure semantic relatedness. Our best heuristic achieves an F-score of 93.17% on a test dataset with gold-standard labels obtained using manual annotation.

Leveraging Diverse Lexical Chains to Construct Essays for Chinese College Entrance Examination
Liunian Li | Xiaojun Wan | Jin-ge Yao | Siming Yan

In this work we study the challenging task of automatically constructing essays for Chinese college entrance examination where the topic is specified in advance. We explore a sentence extraction framework based on diversified lexical chains to capture coherence and richness. Experimental analysis shows the effectiveness of our approach and reveals the importance of information richness in essay writing.

Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task
Ting Han | David Schlangen

While language conveys meaning largely symbolically, actual communication acts typically contain iconic elements as well: People gesture while they speak, or may even draw sketches while explaining something. Image retrieval prima facie seems like a task that could profit from combined symbolic and iconic reference, but it is typically set up to work either from language only, or via (iconic) sketches with no verbal contribution. Using a model of grounded language semantics and a model of sketch-to-image mapping, we show that adding even very reduced iconic information to a verbal image description improves recall. Verbal descriptions paired with fully detailed sketches still perform better than these sketches alone. We see these results as supporting the assumption that natural user interfaces should respond to multimodal input, where possible, rather than just language alone.

Grammatical Error Correction with Neural Reinforcement Learning
Keisuke Sakaguchi | Matt Post | Benjamin Van Durme

We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE. We demonstrate that NRL outperforms MLE both in human and automated evaluation metrics, achieving the state-of-the-art on a fluency-oriented GEC corpus.

Coreference Resolution on Math Problem Text in Japanese
Takumi Ito | Takuya Matsuzaki | Satoshi Sato

This paper describes a coreference resolution system for math problem text. Case frame dictionaries and a math taxonomy are utilized for supplying domain knowledge. The system deals with various anaphoric phenomena beyond well-studied entity coreferences.

Utilizing Visual Forms of Japanese Characters for Neural Review Classification
Yota Toyama | Makoto Miwa | Yutaka Sasaki

We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using convolutional neural networks. It then constructs document embeddings from the character embeddings based on Hierarchical Attention Networks, which represent the documents based on attention mechanisms from a character level to a sentence level. The document embeddings are finally used to predict the labels of documents. Our method provides a way to exploit visual features of characters in languages with ideograms and logograms. In the experiments, our method achieved an accuracy comparable to a character embedding-based model while our method has much fewer parameters since it does not need to keep embeddings of thousands of characters.

A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition
Dingquan Wang | Nanyun Peng | Kevin Duh

We show how to adapt bilingual word embeddings (BWE’s) to bootstrap a cross-lingual name-entity recognition (NER) system in a language with no labeled data. We assume a setting where we are given a comparable corpus with NER labels for the source language only; our goal is to build a NER model for the target language. The proposed multi-task model jointly trains bilingual word embeddings while optimizing a NER objective. This creates word embeddings that are both shared between languages and fine-tuned for the NER task.

Investigating the Effect of Conveying Understanding Results in Chat-Oriented Dialogue Systems
Koh Mitsuda | Ryuichiro Higashinaka | Junji Tomita

In dialogue systems, conveying understanding results of user utterances is important because it enables users to feel understood by the system. However, it is not clear what types of understanding results should be conveyed to users; some utterances may be offensive and some may be too commonsensical. In this paper, we explored the effect of conveying understanding results of user utterances in a chat-oriented dialogue system by an experiment using human subjects. As a result, we found that only certain types of understanding results, such as those related to a user’s permanent state, are effective to improve user satisfaction. This paper clarifies the types of understanding results that can be safely uttered by a system.

Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences
Ebuka Ibeke | Chenghua Lin | Adam Wyner | Mohamad Hardyman Barawi

Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.

CWIG3G2 - Complex Word Identification Task across Three Text Genres and Two User Groups
Seid Muhie Yimam | Sanja Štajner | Martin Riedl | Chris Biemann

Complex word identification (CWI) is an important task in text accessibility. However, due to the scarcity of CWI datasets, previous studies have only addressed this problem on Wikipedia sentences and have solely taken into account the needs of non-native English speakers. We collect a new CWI dataset (CWIG3G2) covering three text genres News, WikiNews, and Wikipedia) annotated by both native and non-native English speakers. Unlike previous datasets, we cover single words, as well as complex phrases, and present them for judgment in a paragraph context. We present the first study on cross-genre and cross-group CWI, showing measurable influences in native language and genre types.

Generating Stylistically Consistent Dialog Responses with Transfer Learning
Reina Akama | Kazuaki Inada | Naoya Inoue | Sosuke Kobayashi | Kentaro Inui

We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain.

Learning to Explain Non-Standard English Words and Phrases
Ke Ni | William Yang Wang

We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from Unlike prior studies that focus on matching keywords from a slang dictionary, we investigate the possibility of learning a neural sequence-to-sequence model that generates explanations of unseen non-standard English expressions given context. We propose a dual encoder approach—a word-level encoder learns the representation of context, and a second character-level encoder to learn the hidden representation of the target non-standard expression. Our model can produce reasonable definitions of new non-standard English expressions given their context with certain confidence.

Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging
Yllias Chali | Moin Tanvee | Mir Tafseer Nayeem

We propose a submodular function-based summarization system which integrates three important measures namely importance, coverage, and non-redundancy to detect the important sentences for the summary. We design monotone and submodular functions which allow us to apply an efficient and scalable greedy algorithm to obtain informative and well-covered summaries. In addition, we integrate two abstraction-based methods namely sentence compression and merging for generating an abstractive sentence set. We design our summarization models for both generic and query-focused summarization. Experimental results on DUC-2004 and DUC-2007 datasets show that our generic and query-focused summarizers have outperformed the state-of-the-art summarization systems in terms of ROUGE-1 and ROUGE-2 recall and F-measure.

Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network
Lisheng Fu | Thien Huu Nguyen | Bonan Min | Ralph Grishman

Relations are expressed in many domains such as newswire, weblogs and phone conversations. Trained on a source domain, a relation extractor’s performance degrades when applied to target domains other than the source. A common yet labor-intensive method for domain adaptation is to construct a target-domain-specific labeled dataset for adapting the extractor. In response, we present an unsupervised domain adaptation method which only requires labels from the source domain. Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier. The two components are optimized jointly to learn a domain-independent representation for prediction on the target domain. Our model outperforms the state-of-the-art on all three test domains of ACE 2005.

Lexical Simplification with the Deep Structured Similarity Model
Lis Pereira | Xiaodong Liu | John Lee

We explore the application of a Deep Structured Similarity Model (DSSM) to ranking in lexical simplification. Our results show that the DSSM can effectively capture fine-grained features to perform semantic matching when ranking substitution candidates, outperforming the state-of-the-art on two standard datasets used for the task.

Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction
Yuta Hitomi | Hideaki Tamori | Naoaki Okazaki | Kentaro Inui

This paper explores the idea of robot editors, automated proofreaders that enable journalists to improve the quality of their articles. We propose a novel neural model of multi-task learning that both generates proofread sentences and predicts the editing operations required to rewrite the source sentences and create the proofread ones. The model is trained using logs of the revisions made professional editors revising draft newspaper articles written by journalists. Experiments demonstrate the effectiveness of our multi-task learning approach and the potential value of using revision logs for this task.

An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering
Charles Chen | Razvan Bunescu

The automation of tasks in community question answering (cQA) is dominated by machine learning approaches, whose performance is often limited by the number of training examples. Starting from a neural sequence learning approach with attention, we explore the impact of two data augmentation techniques on question ranking performance: a method that swaps reference questions with their paraphrases, and training on examples automatically selected from external datasets. Both methods are shown to lead to substantial gains in accuracy over a strong baseline. Further improvements are obtained by changing the model architecture to mirror the structure seen in the data.

Deriving Consensus for Multi-Parallel Corpora: an English Bible Study
Patrick Xia | David Yarowsky

What can you do with multiple noisy versions of the same text? We present a method which generates a single consensus between multi-parallel corpora. By maximizing a function of linguistic features between word pairs, we jointly learn a single corpus-wide multiway alignment: a consensus between 27 versions of the English Bible. We additionally produce English paraphrases, word-level distributions of tags, and consensus dependency parses. Our method is language independent and applicable to any multi-parallel corpora. Given the Bible’s unique role as alignable bitext for over 800 of the world’s languages, this consensus alignment and resulting resources offer value for multilingual annotation projection, and also shed potential insights into the Bible itself.


pdf (full)
bib (full)
Proceedings of the IJCNLP 2017, System Demonstrations

pdf bib
Proceedings of the IJCNLP 2017, System Demonstrations
Seong-Bae Park | Thepchai Supnithi

pdf bib
MASSAlign: Alignment and Annotation of Comparable Documents
Gustavo Paetzold | Fernando Alva-Manchego | Lucia Specia

We introduce MASSAlign: a Python library for the alignment and annotation of monolingual comparable documents. MASSAlign offers easy-to-use access to state of the art algorithms for paragraph and sentence-level alignment, as well as novel algorithms for word-level annotation of transformation operations between aligned sentences. In addition, MASSAlign provides a visualization module to display and analyze the alignments and annotations performed.

pdf bib
CADET: Computer Assisted Discovery Extraction and Translation
Benjamin Van Durme | Tom Lippincott | Kevin Duh | Deana Burchfield | Adam Poliak | Cash Costello | Tim Finin | Scott Miller | James Mayfield | Philipp Koehn | Craig Harman | Dawn Lawrie | Chandler May | Max Thomas | Annabelle Carrell | Julianne Chaloux | Tongfei Chen | Alex Comerford | Mark Dredze | Benjamin Glass | Shudong Hao | Patrick Martin | Pushpendre Rastogi | Rashmi Sankepally | Travis Wolfe | Ying-Ying Tran | Ted Zhang

Computer Assisted Discovery Extraction and Translation (CADET) is a workbench for helping knowledge workers find, label, and translate documents of interest. It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users. This open-source framework allows for easy development of new research prototypes using a micro-service architecture based atop Docker and Apache Thrift.

WiseReporter: A Korean Report Generation System
Yunseok Noh | Su Jeong Choi | Seong-Bae Park | Se-Young Park

We demonstrate a report generation system called WiseReporter. The WiseReporter generates a text report of a specific topic which is usually given as a keyword by verbalizing knowledge base facts involving the topic. This demonstration does not demonstate only the report itself, but also the processes how the sentences for the report are generated. We are planning to enhance WiseReporter in the future by adding data analysis based on deep learning architecture and text summarization.

Encyclolink: A Cross-Encyclopedia,Cross-language Article-Linking System and Web-based Search Interface
Yu-Chun Wang | Ka Ming Wong | Chun-Kai Wu | Chao-Lin Pan | Richard Tzong-Han Tsai

Cross-language article linking (CLAL) is the task of finding corresponding article pairs across encyclopedias of different languages. In this paper, we present Encyclolink, a web-based CLAL search interface designed to help users find equivalent encyclopedia articles in Baidu Baike for a given English Wikipedia article title query. Encyclolink is powered by our cross-encyclopedia entity embedding CLAL system (0.8 MRR). The browser-based Interface provides users with a clear and easily readable preview of the contents of retrieved articles for comparison.

A Telecom-Domain Online Customer Service Assistant Based on Question Answering with Word Embedding and Intent Classification
Jui-Yang Wang | Min-Feng Kuo | Jen-Chieh Han | Chao-Chuang Shih | Chun-Hsun Chen | Po-Ching Lee | Richard Tzong-Han Tsai

In the paper, we propose an information retrieval based (IR-based) Question Answering (QA) system to assist online customer service staffs respond users in the telecom domain. When user asks a question, the system retrieves a set of relevant answers and ranks them. Moreover, our system uses a novel reranker to enhance the ranking result of information retrieval.It employs the word2vec model to represent the sentences as vectors. It also uses a sub-category feature, predicted by the k-nearest neighbor algorithm. Finally, the system returns the top five candidate answers, making online staffs find answers much more efficiently.

TOTEMSS: Topic-based, Temporal Sentiment Summarisation for Twitter
Bo Wang | Maria Liakata | Adam Tsakalidis | Spiros Georgakopoulos Kolaitis | Symeon Papadopoulos | Lazaros Apostolidis | Arkaitz Zubiaga | Rob Procter | Yiannis Kompatsiaris

We present a system for time sensitive, topic based summarisation of the sentiment around target entities and topics in collections of tweets. We describe the main elements of the system and illustrate its functionality with two examples of sentiment analysis of topics related to the 2017 UK general election.

MUSST: A Multilingual Syntactic Simplification Tool
Carolina Scarton | Alessio Palmero Aprosio | Sara Tonelli | Tamara Martín Wanton | Lucia Specia

We describe MUSST, a multilingual syntactic simplification tool. The tool supports sentence simplifications for English, Italian and Spanish, and can be easily extended to other languages. Our implementation includes a set of general-purpose simplification rules, as well as a sentence selection module (to select sentences to be simplified) and a confidence model (to select only promising simplifications). The tool was implemented in the context of the European project SIMPATICO on text simplification for Public Administration (PA) texts. Our evaluation on sentences in the PA domain shows that we obtain correct simplifications for 76% of the simplified cases in English, 71% of the cases in Spanish. For Italian, the results are lower (38%) but the tool is still under development.

XMU Neural Machine Translation Online Service
Boli Wang | Zhixing Tan | Jinming Hu | Yidong Chen | Xiaodong Shi

We demonstrate a neural machine translation web service. Our NMT service provides web-based translation interfaces for a variety of language pairs. We describe the architecture of NMT runtime pipeline and the training details of NMT models. We also show several applications of our online translation interfaces.

Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking
Longyue Wang | Jinhua Du | Liangyou Li | Zhaopeng Tu | Andy Way | Qun Liu

We showcase TODAY, a semantics-enhanced task-oriented dialogue translation system, whose novelties are: (i) task-oriented named entity (NE) definition and a hybrid strategy for NE recognition and translation; and (ii) a novel grounded semantic method for dialogue understanding and task-order management. TODAY is a case-study demo which can efficiently and accurately assist customers and agents in different languages to reach an agreement in a dialogue for the hotel booking.

NNVLP: A Neural Network-Based Vietnamese Language Processing Toolkit
Thai-Hoang Pham | Xuan-Khoai Pham | Tuan-Anh Nguyen | Phuong Le-Hong

This paper demonstrates neural network-based toolkit namely NNVLP for essential Vietnamese language processing tasks including part-of-speech (POS) tagging, chunking, Named Entity Recognition (NER). Our toolkit is a combination of bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Network (CNN), Conditional Random Field (CRF), using pre-trained word embeddings as input, which outperforms previously published toolkits on these three tasks. We provide both of API and web demo for this toolkit.

ClassifierGuesser: A Context-based Classifier Prediction System for Chinese Language Learners
Nicole Peinelt | Maria Liakata | Shu-Kai Hsieh

Classifiers are function words that are used to express quantities in Chinese and are especially difficult for language learners. In contrast to previous studies, we argue that the choice of classifiers is highly contextual and train context-aware machine learning models based on a novel publicly available dataset, outperforming previous baselines. We further present use cases for our database and models in an interactive demo system.

Automatic Difficulty Assessment for Chinese Texts
John Lee | Meichun Liu | Chun Yin Lam | Tak On Lau | Bing Li | Keying Li

We present a web-based interface that automatically assesses reading difficulty of Chinese texts. The system performs word segmentation, part-of-speech tagging and dependency parsing on the input text, and then determines the difficulty levels of the vocabulary items and grammatical constructions in the text. Furthermore, the system highlights the words and phrases that must be simplified or re-written in order to conform to the user-specified target difficulty level. Evaluation results show that the system accurately identifies the vocabulary level of 89.9% of the words, and detects grammar points at 0.79 precision and 0.83 recall.

Verb Replacer: An English Verb Error Correction System
Yu-Hsuan Wu | Jhih-Jie Chen | Jason Chang

According to the analysis of Cambridge Learner Corpus, using a wrong verb is the most common type of grammatical errors. This paper describes Verb Replacer, a system for detecting and correcting potential verb errors in a given sentence. In our approach, alternative verbs are considered to replace the verb based on an error-annotated corpus and verb-object collocations. The method involves applying regression on channel models, parsing the sentence, identifying the verbs, retrieving a small set of alternative verbs, and evaluating each alternative. Our method combines and improves channel and language models, resulting in high recall of detecting and correcting verb misuse.

Learning Synchronous Grammar Patterns for Assisted Writing for Second Language Learners
Chi-En Wu | Jhih-Jie Chen | Jim Chang | Jason Chang

In this paper, we present a method for extracting Synchronous Grammar Patterns (SGPs) from a given parallel corpus in order to assisted second language learners in writing. A grammar pattern consists of a head word (verb, noun, or adjective) and its syntactic environment. A synchronous grammar pattern describes a grammar pattern in the target language (e.g., English) and its counterpart in an other language (e.g., Mandarin), serving the purpose of native language support. Our method involves identifying the grammar patterns in the target language, aligning these patterns with the target language patterns, and finally filtering valid SGPs. The extracted SGPs with examples are then used to develop a prototype writing assistant system, called WriteAhead/bilingual. Evaluation on a set of randomly selected SGPs shows that our system provides satisfactory writing suggestions for English as a Second Language (ESL) learners.

Guess What: A Question Answering Game via On-demand Knowledge Validation
Yu-Sheng Li | Chien-Hui Tseng | Chian-Yun Huang | Wei-Yun Ma

In this paper, we propose an idea of ondemand knowledge validation and fulfill the idea through an interactive Question-Answering (QA) game system, which is named Guess What. An object (e.g. dog) is first randomly chosen by the system, and then a user can repeatedly ask the system questions in natural language to guess what the object is. The system would respond with yes/no along with a confidence score. Some useful hints can also be given if needed. The proposed framework provides a pioneering example of on-demand knowledge validation in dialog environment to address such needs in AI agents/chatbots. Moreover, the released log data that the system gathered can be used to identify the most critical concepts/attributes of an existing knowledge base, which reflects human’s cognition about the world.

STCP: Simplified-Traditional Chinese Conversion and Proofreading
Jiarui Xu | Xuezhe Ma | Chen-Tse Tsai | Eduard Hovy

This paper aims to provide an effective tool for conversion between Simplified Chinese and Traditional Chinese. We present STCP, a customizable system comprising statistical conversion model, and proofreading web interface. Experiments show that our system achieves comparable character-level conversion performance with the state-of-art systems. In addition, our proofreading interface can effectively support diagnostics and data annotation. STCP is available at

Deep Neural Network based system for solving Arithmetic Word problems
Purvanshi Mehta | Pruthwik Mishra | Vinayak Athavale | Manish Shrivastava | Dipti Sharma

This paper presents DILTON a system which solves simple arithmetic word problems. DILTON uses a Deep Neural based model to solve math word problems. DILTON divides the question into two parts - worldstate and query. The worldstate and the query are processed separately in two different networks and finally, the networks are merged to predict the final operation. We report the first deep learning approach for the prediction of operation between two numbers. DILTON learns to predict operations with 88.81% accuracy in a corpus of primary school questions.


pdf (full)
bib (full)
Proceedings of the IJCNLP 2017, Shared Tasks

pdf bib
Proceedings of the IJCNLP 2017, Shared Tasks
Chao-Hong Liu | Preslav Nakov | Nianwen Xue

pdf bib
IJCNLP-2017 Task 1: Chinese Grammatical Error Diagnosis
Gaoqi Rao | Baolin Zhang | Endong Xun | Lung-Hao Lee

This paper presents the IJCNLP 2017 shared task for Chinese grammatical error diagnosis (CGED) which seeks to identify grammatical error types and their range of occurrence within sentences written by learners of Chinese as foreign language. We describe the task definition, data preparation, performance metrics, and evaluation results. Of the 13 teams registered for this shared task, 5 teams developed the system and submitted a total of 13 runs. We expected this evaluation campaign could lead to the development of more advanced NLP techniques for educational applications, especially for Chinese error detection. All data sets with gold standards and scoring scripts are made publicly available to researchers.

pdf bib
IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases
Liang-Chih Yu | Lung-Hao Lee | Jin Wang | Kam-Fai Wong

This paper presents the IJCNLP 2017 shared task on Dimensional Sentiment Analysis for Chinese Phrases (DSAP) which seeks to identify a real-value sentiment score of Chinese single words and multi-word phrases in the both valence and arousal dimensions. Valence represents the degree of pleasant and unpleasant (or positive and negative) feelings, and arousal represents the degree of excitement and calm. Of the 19 teams registered for this shared task for two-dimensional sentiment analysis, 13 submitted results. We expected that this evaluation campaign could produce more advanced dimensional sentiment analysis techniques, especially for Chinese affective computing. All data sets with gold standards and scoring script are made publicly available to researchers.

IJCNLP-2017 Task 3: Review Opinion Diversification (RevOpiD-2017)
Anil Kumar Singh | Avijit Thawani | Mayank Panchal | Anubhav Gupta | Julian McAuley

Unlike Entity Disambiguation in web search results, Opinion Disambiguation is a relatively unexplored topic. RevOpiD shared task at IJCNLP-2107 aimed to attract attention towards this research problem. In this paper, we summarize the first run of this task and introduce a new dataset that we have annotated for the purpose of evaluating Opinion Mining, Summarization and Disambiguation methods.

IJCNLP-2017 Task 4: Customer Feedback Analysis
Chao-Hong Liu | Yasufumi Moriya | Alberto Poncelas | Declan Groves

This document introduces the IJCNLP 2017 Shared Task on Customer Feedback Analysis. In this shared task we have prepared corpora of customer feedback in four languages, i.e. English, French, Spanish and Japanese. They were annotated in a common meanings categorization, which was improved from an ADAPT-Microsoft pivot study on customer feedback. Twenty teams participated in the shared task and twelve of them have submitted prediction results. The results show that performance of prediction meanings of customer feedback is reasonable well in four languages. Nine system description papers are archived in the shared tasks proceeding.

IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations
Shangmin Guo | Kang Liu | Shizhu He | Cao Liu | Jun Zhao | Zhuoyu Wei

The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entrance Examination papers and CK12 website1. The questions are all 4-way multi-choice questions writing in Chinese and English respectively that cover a wide range of subjects, e.g. Biology, History, Life Science and etc. And, all questions are restrained within the elementary and middle school level. During the whole procedure of this task, 7 teams submitted 323 runs in total. This paper describes the collected data, the format and size of these questions, formal run statistics and results, overview and performance statistics of different methods

Alibaba at IJCNLP-2017 Task 1: Embedding Grammatical Features into LSTMs for Chinese Grammatical Error Diagnosis Task
Yi Yang | Pengjun Xie | Jun Tao | Guangwei Xu | Linlin Li | Luo Si

This paper introduces Alibaba NLP team system on IJCNLP 2017 shared task No. 1 Chinese Grammatical Error Diagnosis (CGED). The task is to diagnose four types of grammatical errors which are redundant words (R), missing words (M), bad word selection (S) and disordered words (W). We treat the task as a sequence tagging problem and design some handcraft features to solve it. Our system is mainly based on the LSTM-CRF model and 3 ensemble strategies are applied to improve the performance. At the identification level and the position level our system gets the highest F1 scores. At the position level, which is the most difficult level, we perform best on all metrics.

THU_NGN at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases with Deep LSTM
Chuhan Wu | Fangzhao Wu | Yongfeng Huang | Sixing Wu | Zhigang Yuan

Predicting valence-arousal ratings for words and phrases is very useful for constructing affective resources for dimensional sentiment analysis. Since the existing valence-arousal resources of Chinese are mainly in word-level and there is a lack of phrase-level ones, the Dimensional Sentiment Analysis for Chinese Phrases (DSAP) task aims to predict the valence-arousal ratings for Chinese affective words and phrases automatically. In this task, we propose an approach using a densely connected LSTM network and word features to identify dimensional sentiment on valence and arousal for words and phrases jointly. We use word embedding as major feature and choose part of speech (POS) and word clusters as additional features to train the dense LSTM network. The evaluation results of our submissions (1st and 2nd in average performance) validate the effectiveness of our system to predict valence and arousal dimensions for Chinese words and phrases.

IIIT-H at IJCNLP-2017 Task 3: A Bidirectional-LSTM Approach for Review Opinion Diversification
Pruthwik Mishra | Prathyusha Danda | Silpa Kanneganti | Soujanya Lanka

The Review Opinion Diversification (Revopid-2017) shared task focuses on selecting top-k reviews from a set of reviews for a particular product based on a specific criteria. In this paper, we describe our approaches and results for modeling the ranking of reviews based on their usefulness score, this being the first of the three subtasks under this shared task. Instead of posing this as a regression problem, we modeled this as a classification task where we want to identify whether a review is useful or not. We employed a bi-directional LSTM to represent each review and is used with a softmax layer to predict the usefulness score. We chose the review with highest usefulness score, then find its cosine similarity score with rest of the reviews. This is done in order to ensure diversity in the selection of top-k reviews. On the top-5 list prediction, we finished 3rd while in top-10 list one, we are placed 2nd in the shared task. We have discussed the model and the results in detail in the paper.

Bingo at IJCNLP-2017 Task 4: Augmenting Data using Machine Translation for Cross-linguistic Customer Feedback Classification
Heba Elfardy | Manisha Srivastava | Wei Xiao | Jared Kramer | Tarun Agarwal

The ability to automatically and accurately process customer feedback is a necessity in the private sector. Unfortunately, customer feedback can be one of the most difficult types of data to work with due to the sheer volume and variety of services, products, languages, and cultures that comprise the customer experience. In order to address this issue, our team built a suite of classifiers trained on a four-language, multi-label corpus released as part of the shared task on “Customer Feedback Analysis” at IJCNLP 2017. In addition to standard text preprocessing, we translated each dataset into each other language to increase the size of the training datasets. Additionally, we also used word embeddings in our feature engineering step. Ultimately, we trained classifiers using Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) Recurrent Neural Networks. Overall, we achieved a Macro-Average F-score between 48.7% and 56.0% for the four languages and ranked 3/12 for English, 3/7 for Spanish, 1/8 for French, and 2/7 for Japanese.

ADAPT Centre Cone Team at IJCNLP-2017 Task 5: A Similarity-Based Logistic Regression Approach to Multi-choice Question Answering in an Examinations Shared Task
Daria Dzendzik | Alberto Poncelas | Carl Vogel | Qun Liu

We describe the work of a team from the ADAPT Centre in Ireland in addressing automatic answer selection for the Multi-choice Question Answering in Examinations shared task. The system is based on a logistic regression over the string similarities between question, answer, and additional text. We obtain the highest grade out of six systems: 48.7% accuracy on a validation set (vs. a baseline of 29.45%) and 45.6% on a test set.

YNU-HPCC at IJCNLP-2017 Task 1: Chinese Grammatical Error Diagnosis Using a Bi-directional LSTM-CRF Model
Quanlei Liao | Jin Wang | Jinnan Yang | Xuejie Zhang

Building a system to detect Chinese grammatical errors is a challenge for natural-language processing researchers. As Chinese learners are increasing, developing such a system can help them study Chinese more easily. This paper introduces a bi-directional long short-term memory (BiLSTM) - conditional random field (CRF) model to produce the sequences that indicate an error type for every position of a sentence, since we regard Chinese grammatical error diagnosis (CGED) as a sequence-labeling problem.

CVTE at IJCNLP-2017 Task 1: Character Checking System for Chinese Grammatical Error Diagnosis Task
Xian Li | Peng Wang | Suixue Wang | Guanyu Jiang | Tianyuan You

Grammatical error diagnosis is an important task in natural language processing. This paper introduces CVTE Character Checking System in the NLP-TEA-4 shared task for CGED 2017, we use Bi-LSTM to generate the probability of every character, then take two kinds of strategies to decide whether a character is correct or not. This system is probably more suitable to deal with the error type of bad word selection, which is one of four types of errors, and the rest are words re-dundancy, words missing and words disorder. Finally the second strategy achieves better F1 score than the first one at all of detection level, identification level, position level.

LDCCNLP at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases Using Machine Learning
Peng Zhong | Jingbin Wang

Sentiment analysis on Chinese text has intensively studied. The basic task for related research is to construct an affective lexicon and thereby predict emotional scores of different levels. However, finite lexicon resources make it difficult to effectively and automatically distinguish between various types of sentiment information in Chinese texts. This IJCNLP2017-Task2 competition seeks to automatically calculate Valence and Arousal ratings within the hierarchies of vocabulary and phrases in Chinese. We introduce a regression methodology to automatically recognize continuous emotional values, and incorporate a word embedding technique. In our system, the MAE predictive values of Valence and Arousal were 0.811 and 0.996, respectively, for the sentiment dimension prediction of words in Chinese. In phrase prediction, the corresponding results were 0.822 and 0.489, ranking sixth among all teams.

CKIP at IJCNLP-2017 Task 2: Neural Valence-Arousal Prediction for Phrases
Peng-Hsuan Li | Wei-Yun Ma | Hsin-Yang Wang

CKIP takes part in solving the Dimensional Sentiment Analysis for Chinese Phrases (DSAP) share task of IJCNLP 2017. This task calls for systems that can predict the valence and the arousal of Chinese phrases, which are real values between 1 and 9. To achieve this, functions mapping Chinese character sequences to real numbers are built by regression techniques. In addition, the CKIP phrase Valence-Arousal (VA) predictor depends on knowledge of modifier words and head words. This includes the types of known modifier words, VA of head words, and distributional semantics of both these words. The predictor took the second place out of 13 teams on phrase VA prediction, with 0.444 MAE and 0.935 PCC on valence, and 0.395 MAE and 0.904 PCC on arousal.

CIAL at IJCNLP-2017 Task 2: An Ensemble Valence-Arousal Analysis System for Chinese Words and Phrases
Zheng-Wen Lin | Yung-Chun Chang | Chen-Ann Wang | Yu-Lun Hsieh | Wen-Lian Hsu

Sentiment lexicon is very helpful in dimensional sentiment applications. Because of countless Chinese words, developing a method to predict unseen Chinese words is required. The proposed method can handle both words and phrases by using an ADVWeight List for word prediction, which in turn improves our performance at phrase level. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese phrases. The Mean Absolute Error (MAE) and Pearson’s Correlation Coefficient (PCC) for Valence are 0.723 and 0.835, respectively, and those for Arousal are 0.914 and 0.756, respectively.

Alibaba at IJCNLP-2017 Task 2: A Boosted Deep System for Dimensional Sentiment Analysis of Chinese Phrases
Xin Zhou | Jian Wang | Xu Xie | Changlong Sun | Luo Si

This paper introduces Team Alibaba’s systems participating IJCNLP 2017 shared task No. 2 Dimensional Sentiment Analysis for Chinese Phrases (DSAP). The systems mainly utilize a multi-layer neural networks, with multiple features input such as word embedding, part-of-speech-tagging (POST), word clustering, prefix type, character embedding, cross sentiment input, and AdaBoost method for model training. For word level task our best run achieved MAE 0.545 (ranked 2nd), PCC 0.892 (ranked 2nd) in valence prediction and MAE 0.857 (ranked 1st), PCC 0.678 (ranked 2nd) in arousal prediction. For average performance of word and phrase task we achieved MAE 0.5355 (ranked 3rd), PCC 0.8965 (ranked 3rd) in valence prediction and MAE 0.661 (ranked 3rd), PCC 0.766 (ranked 2nd) in arousal prediction. In the final our submitted system achieved 2nd in mean rank.

NLPSA at IJCNLP-2017 Task 2: Imagine Scenario: Leveraging Supportive Images for Dimensional Sentiment Analysis
Szu-Min Chen | Zi-Yuan Chen | Lun-Wei Ku

Categorical sentiment classification has drawn much attention in the field of NLP, while less work has been conducted for dimensional sentiment analysis (DSA). Recent works for DSA utilize either word embedding, knowledge base features, or bilingual language resources. In this paper, we propose our model for IJCNLP 2017 Dimensional Sentiment Analysis for Chinese Phrases shared task. Our model incorporates word embedding as well as image features, attempting to simulate human’s imaging behavior toward sentiment analysis. Though the performance is not comparable to others in the end, we conduct several experiments with possible reasons discussed, and analyze the drawbacks of our model.

NCYU at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases using Vector Representations
Jui-Feng Yeh | Jian-Cheng Tsai | Bo-Wei Wu | Tai-You Kuang

This paper presents two vector representations proposed by National Chiayi University (NCYU) about phrased-based sentiment detection which was used to compete in dimensional sentiment analysis for Chinese phrases (DSACP) at IJCNLP 2017. The vector-based sentiment phraselike unit analysis models are proposed in this article. E-HowNet-based clustering is used to obtain the values of valence and arousal for sentiment words first. An out-of-vocabulary function is also defined in this article to measure the dimensional emotion values for unknown words. For predicting the corresponding values of sentiment phrase-like unit, a vectorbased approach is proposed here. According to the experimental results, we can find the proposed approach is efficacious.

MainiwayAI at IJCNLP-2017 Task 2: Ensembles of Deep Architectures for Valence-Arousal Prediction
Yassine Benajiba | Jin Sun | Yong Zhang | Zhiliang Weng | Or Biran

This paper introduces Mainiway AI Labs submitted system for the IJCNLP 2017 shared task on Dimensional Sentiment Analysis of Chinese Phrases (DSAP), and related experiments. Our approach consists of deep neural networks with various architectures, and our best system is a voted ensemble of networks. We achieve a Mean Absolute Error of 0.64 in valence prediction and 0.68 in arousal prediction on the test set, both placing us as the 5th ranked team in the competition.

NCTU-NTUT at IJCNLP-2017 Task 2: Deep Phrase Embedding using bi-LSTMs for Valence-Arousal Ratings Prediction of Chinese Phrases
Yen-Hsuan Lee | Han-Yun Yeh | Yih-Ru Wang | Yuan-Fu Liao

In this paper, a deep phrase embedding approach using bi-directional long short-term memory (Bi-LSTM) is proposed to predict the valence-arousal ratings of Chinese words and phrases. It adopts a Chinese word segmentation frontend, a local order-aware word, a global phrase embedding representations and a deep regression neural network (DRNN) model. The performance of the proposed method was benchmarked by the IJCNLP 2017 shared task 2. According the official evaluation results, our best system achieved mean rank 6.5 among all 24 submissions.

NTOUA at IJCNLP-2017 Task 2: Predicting Sentiment Scores of Chinese Words and Phrases
Chuan-Jie Lin | Hao-Tsung Chang

This paper describes the approaches of sentimental score prediction in the NTOU DSA system participating in DSAP this year. The modules to predict scores for words are adapted from our system last year. The approach to predict scores for phrases is keyword-based machine learning method. The performance of our system is good in predicting scores of phrases.

CYUT at IJCNLP-2017 Task 3: System Report for Review Opinion Diversification
Shih-Hung Wu | Su-Yu Chang | Liang-Pu Chen

Review Opinion Diversification (RevOpiD) 2017 is a shared task which is held in International Joint Conference on Natural Language Processing (IJCNLP). The shared task aims at selecting top-k reviews, as a summary, from a set of re-views. There are three subtasks in RevOpiD: helpfulness ranking, rep-resentativeness ranking, and ex-haustive coverage ranking. This year, our team submitted runs by three models. We focus on ranking reviews based on the helpfulness of the reviews. In the first two models, we use linear regression with two different loss functions. First one is least squares, and second one is cross entropy. The third run is a random baseline. For both k=5 and k=10, our second model gets the best scores in the official evaluation metrics.

JUNLP at IJCNLP-2017 Task 3: A Rank Prediction Model for Review Opinion Diversification
Monalisa Dey | Anupam Mondal | Dipankar Das

IJCNLP-17 Review Opinion Diversification (RevOpiD-2017) task has been designed for ranking the top-k reviews of a product from a set of reviews, which assists in identifying a summarized output to express the opinion of the entire review set. The task is divided into three independent subtasks as subtask-A,subtask-B, and subtask-C. Each of these three subtasks selects the top-k reviews based on helpfulness, representativeness, and exhaustiveness of the opinions expressed in the review set individually. In order to develop the modules and predict the rank of reviews for all three subtasks, we have employed two well-known supervised classifiers namely, Naïve Bayes and Logistic Regression on the top of several extracted features such as the number of nouns, number of verbs, and number of sentiment words etc from the provided datasets. Finally, the organizers have helped to validate the predicted outputs for all three subtasks by using their evaluation metrics. The metrics provide the scores of list size 5 as (0.80 (mth)) for subtask-A, (0.86 (cos), 0.87 (cos d), 0.71 (cpr), 4.98 (a-dcg), and 556.94 (wt)) for subtask B, and (10.94 (unwt) and 0.67 (recall)) for subtask C individually.

All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages
Barbara Plank

We present All-In-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams. Our model is simple, easily extendable yet very effective, overall ranking 1st (out of 12 teams) in the IJCNLP 2017 shared task on customer feedback analysis in four languages: English, French, Japanese and Spanish.

SentiNLP at IJCNLP-2017 Task 4: Customer Feedback Analysis Using a Bi-LSTM-CNN Model
Shuying Lin | Huosheng Xie | Liang-Chih Yu | K. Robert Lai

The analysis of customer feedback is useful to provide good customer service. There are a lot of online customer feedback are produced. Manual classification is impractical because the high volume of data. Therefore, the automatic classification of the customer feedback is of importance for the analysis system to identify meanings or intentions that the customer express. The aim of shared Task 4 of IJCNLP 2017 is to classify the customer feedback into six tags categorization. In this paper, we present a system that uses word embeddings to express the feature of the sentence in the corpus and the neural network as the classifier to complete the shared task. And then the ensemble method is used to get final predictive result. The proposed method get ranked first among twelve teams in terms of micro-averaged F1 and second for accura-cy metric.

IIIT-H at IJCNLP-2017 Task 4: Customer Feedback Analysis using Machine Learning and Neural Network Approaches
Prathyusha Danda | Pruthwik Mishra | Silpa Kanneganti | Soujanya Lanka

The IJCNLP 2017 shared task on Customer Feedback Analysis focuses on classifying customer feedback into one of a predefined set of categories or classes. In this paper, we describe our approach to this problem and the results on four languages, i.e. English, French, Japanese and Spanish. Our system implemented a bidirectional LSTM (Graves and Schmidhuber, 2005) using pre-trained glove (Pennington et al., 2014) and fastText (Joulin et al., 2016) embeddings, and SVM (Cortes and Vapnik, 1995) with TF-IDF vectors for classifying the feedback data which is described in the later sections. We also tried different machine learning techniques and compared the results in this paper. Out of the 12 participating teams, our systems obtained 0.65, 0.86, 0.70 and 0.56 exact accuracy score in English, Spanish, French and Japanese respectively. We observed that our systems perform better than the baseline systems in three languages while we match the baseline accuracy for Japanese on our submitted systems. We noticed significant improvements in Japanese in later experiments, matching the highest performing system that was submitted in the shared task, which we will discuss in this paper.

ADAPT at IJCNLP-2017 Task 4: A Multinomial Naive Bayes Classification Approach for Customer Feedback Analysis task
Pintu Lohar | Koel Dutta Chowdhury | Haithem Afli | Mohammed Hasanuzzaman | Andy Way

In this age of the digital economy, promoting organisations attempt their best to engage the customers in the feedback provisioning process. With the assistance of customer insights, an organisation can develop a better product and provide a better service to its customer. In this paper, we analyse the real world samples of customer feedback from Microsoft Office customers in four languages, i.e., English, French, Spanish and Japanese and conclude a five-plus-one-classes categorisation (comment, request, bug, complaint, meaningless and undetermined) for meaning classification. The task is to %access multilingual corpora annotated by the proposed meaning categorization scheme and develop a system to determine what class(es) the customer feedback sentences should be annotated as in four languages. We propose following approaches to accomplish this task: (i) a multinomial naive bayes (MNB) approach for multi-label classification, (ii) MNB with one-vs-rest classifier approach, and (iii) the combination of the multilabel classification-based and the sentiment classification-based approach. Our best system produces F-scores of 0.67, 0.83, 0.72 and 0.7 for English, Spanish, French and Japanese, respectively. The results are competitive to the best ones for all languages and secure 3rd and 5th position for Japanese and French, respectively, among all submitted systems.

OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis
Dushyanta Dhyani

This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook’s Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28% for both) and French (70% and 73.17% respectively) task, and outperformed all the other models on comment (87.28%) and meaningless (51.85%) tags using Micro Average F1 by Tags metric for the French task.

YNU-HPCC at IJCNLP-2017 Task 4: Attention-based Bi-directional GRU Model for Customer Feedback Analysis Task of English
Nan Wang | Jin Wang | Xuejie Zhang

This paper describes our submission to IJCNLP 2017 shared task 4, for predicting the tags of unseen customer feedback sentences, such as comments, complaints, bugs, requests, and meaningless and undetermined statements. With the use of a neural network, a large number of deep learning methods have been developed, which perform very well on text classification. Our ensemble classification model is based on a bi-directional gated recurrent unit and an attention mechanism which shows a 3.8% improvement in classification accuracy. To enhance the model performance, we also compared it with several word-embedding models. The comparative results show that a combination of both word2vec and GloVe achieves the best performance.

NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis
Somnath Banerjee | Partha Pakray | Riyanka Manna | Dipankar Das | Alexander Gelbukh

In this paper, we describe a deep learning framework for analyzing the customer feedback as part of our participation in the shared task on Customer Feedback Analysis at the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017). A Convolutional Neural Network (CNN) based deep neural network model was employed for the customer feedback task. The proposed system was evaluated on two languages, namely, English and French.

IITP at IJCNLP-2017 Task 4: Auto Analysis of Customer Feedback using CNN and GRU Network
Deepak Gupta | Pabitra Lenka | Harsimran Bedi | Asif Ekbal | Pushpak Bhattacharyya

Analyzing customer feedback is the best way to channelize the data into new marketing strategies that benefit entrepreneurs as well as customers. Therefore an automated system which can analyze the customer behavior is in great demand. Users may write feedbacks in any language, and hence mining appropriate information often becomes intractable. Especially in a traditional feature-based supervised model, it is difficult to build a generic system as one has to understand the concerned language for finding the relevant features. In order to overcome this, we propose deep Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) based approaches that do not require handcrafting of features. We evaluate these techniques for analyzing customer feedback sentences on four languages, namely English, French, Japanese and Spanish. Our empirical analysis shows that our models perform well in all the four languages on the setups of IJCNLP Shared Task on Customer Feedback Analysis. Our model achieved the second rank in French, with an accuracy of 71.75% and third ranks for all the other languages.

YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations
Min Wang | Qingxun Liu | Peng Ding | Yongbin Li | Xiaobing Zhou

In this paper, we perform convolutional neural networks (CNN) to learn the joint representations of question-answer pairs first, then use the joint representations as the inputs of the long short-term memory (LSTM) with attention to learn the answer sequence of a question for labeling the matching quality of each answer. We also incorporating external knowledge by training Word2Vec on Flashcards data, thus we get more compact embedding. Experimental results show that our method achieves better or comparable performance compared with the baseline system. The proposed approach achieves the accuracy of 0.39, 0.42 in English valid set, test set, respectively.

ALS at IJCNLP-2017 Task 5: Answer Localization System for Multi-Choice Question Answering in Exams
Changliang Li | Cunliang Kong

Multi-choice question answering in exams is a typical QA task. To accomplish this task, we present an answer localization method to locate answers shown in web pages, considering structural information and semantic information both. Using this method as basis, we analyze sentences and paragraphs appeared on web pages to get predictions. With this answer localization system, we get effective results on both validation dataset and test dataset.

MappSent at IJCNLP-2017 Task 5: A Textual Similarity Approach Applied to Multi-choice Question Answering in Examinations
Amir Hazem

In this paper we present MappSent, a textual similarity approach that we applied to the multi-choice question answering in exams shared task. MappSent has initially been proposed for question-to-question similarity hazem2017. In this work, we present the results of two adaptations of MappSent for the question answering task on the English dataset.

YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attention-based LSTM Model
Hang Yuan | You Zhang | Jin Wang | Xuejie Zhang

A shared task is a typical question answering task that aims to test how accurately the participants can answer the questions in exams. Typically, for each question, there are four candidate answers, and only one of the answers is correct. The existing methods for such a task usually implement a recurrent neural network (RNN) or long short-term memory (LSTM). However, both RNN and LSTM are biased models in which the words in the tail of a sentence are more dominant than the words in the header. In this paper, we propose the use of an attention-based LSTM (AT-LSTM) model for these tasks. By adding an attention mechanism to the standard LSTM, this model can more easily capture long contextual information.

JU NITM at IJCNLP-2017 Task 5: A Classification Approach for Answer Selection in Multi-choice Question Answering System
Sandip Sarkar | Dipankar Das | Partha Pakray

This paper describes the participation of the JU NITM team in IJCNLP-2017 Task 5: “Multi-choice Question Answering in Examinations”. The main aim of this shared task is to choose the correct option for each multi-choice question. Our proposed model includes vector representations as feature and machine learning for classification. At first we represent question and answer in vector space and after that find the cosine similarity between those two vectors. Finally we apply classification approach to find the correct answer. Our system was only developed for the English language, and it obtained an accuracy of 40.07% for test dataset and 40.06% for valid dataset.


pdf (full)
bib (full)
Proceedings of the IJCNLP 2017, Tutorial Abstracts

pdf bib
Proceedings of the IJCNLP 2017, Tutorial Abstracts
Sadao Kurohashi | Michael Strube

pdf bib
Deep Learning in Lexical Analysis and Parsing
Wanxiang Che | Yue Zhang

Neural networks, also with a fancy name deep learning, just right can overcome the above “feature engineering” problem. In theory, they can use non-linear activation functions and multiple layers to automatically find useful features. The novel network structures, such as convolutional or recurrent, help to reduce the difficulty further. These deep learning models have been successfully used for lexical analysis and parsing. In this tutorial, we will give a review of each line of work, by contrasting them with traditional statistical methods, and organizing them in consistent orders.

pdf bib
Multilingual Vector Representations of Words, Sentences, and Documents
Gerard de Melo

Neural vector representations are now ubiquitous in all subfields of natural language processing and text mining. While methods such as word2vec and GloVe are well-known, this tutorial focuses on multilingual and cross-lingual vector representations, of words, but also of sentences and documents as well.

Open-Domain Neural Dialogue Systems
Yun-Nung Chen | Jianfeng Gao

In the past decade, spoken dialogue systems have been the most prominent component in today’s personal assistants. A lot of devices have incorporated dialogue system modules, which allow users to speak naturally in order to finish tasks more efficiently. The traditional conversational systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. Nevertheless, applying deep learning technologies for building robust and scalable dialogue systems is still a challenging task and an open research area as it requires deeper understanding of the classic pipelines as well as detailed knowledge on the benchmark of the models of the prior work and the recent state-of-the-art work. Therefore, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building task-oriented and chit-chat dialogue systems, and summarizing the challenges. We target the audience of students and practitioners who have some deep learning background, who want to get more familiar with conversational dialogue systems.

Neural Machine Translation: Basics, Practical Aspects and Recent Trends
Fabien Cromieres | Toshiaki Nakazawa | Raj Dabre

Machine Translation (MT) is a sub-field of NLP which has experienced a number of paradigm shifts since its inception. Up until 2014, Phrase Based Statistical Machine Translation (PBSMT) approaches used to be the state of the art. In late 2014, Neural Machine Translation (NMT) was introduced and was proven to outperform all PBSMT approaches by a significant margin. Since then, the NMT approaches have undergone several transformations which have pushed the state of the art even further. This tutorial is primarily aimed at researchers who are either interested in or are fairly new to the world of NMT and want to obtain a deep understanding of NMT fundamentals. Because it will also cover the latest developments in NMT, it should also be useful to attendees with some experience in NMT.

The Ultimate Presentation Makeup Tutorial: How to Polish your Posters, Slides and Presentations Skills
Gustavo Paetzold | Lucia Specia

There is no question that our research community have, and still has been producing an insurmountable amount of interesting strategies, models and tools to a wide array of problems and challenges in diverse areas of knowledge. But for as long as interesting work has existed, we’ve been plagued by a great unsolved mystery: how come there is so much interesting work being published in conferences, but not as many interesting and engaging posters and presentations being featured in them? In this tutorial, we present practical step-by-step makeup solutions for poster, slides and oral presentations in order to help researchers who feel like they are not able to convey the importance of their research to the community in conferences.

The Challenge of Composition in Distributional and Formal Semantics
Ran Tian | Koji Mineshima | Pascual Martínez-Gómez

This is tutorial proposal. Abstract is as follows: The principle of compositionality states that the meaning of a complete sentence must be explained in terms of the meanings of its subsentential parts; in other words, each syntactic operation should have a corresponding semantic operation. In recent years, it has been increasingly evident that distributional and formal semantics are complementary in addressing composition; while the distributional/vector-based approach can naturally measure semantic similarity (Mitchell and Lapata, 2010), the formal/symbolic approach has a long tradition within logic-based semantic frameworks (Montague, 1974) and can readily be connected to theorem provers or databases to perform complicated tasks. In this tutorial, we will cover recent efforts in extending word vectors to account for composition and reasoning, the various challenging phenomena observed in composition and addressed by formal semantics, and a hybrid approach that combines merits of the two. Outline and introduction to instructors are found in the submission. Ran Tian has taught a tutorial at the Annual Meeting of the Association for Natural Language Processing in Japan, 2015. The estimated audience size was about one hundred. Only a limited part of the contents in this tutorial is drawn from the previous one. Koji Mineshima has taught a one-week course at the 28th European Summer School in Logic, Language and Information (ESSLLI2016), together with Prof. Daisuke Bekki. Only a few contents are the same with this tutorial. Tutorials on “CCG Semantic Parsing” have been given in ACL2013, EMNLP2014, and AAAI2015. A coming tutorial on “Deep Learning for Semantic Composition” will be given in ACL2017. Contents in these tutorials are somehow related to but not overlapping with our proposal.